From 5e714ecb4a40561c2a2e6a54ff8c4d787cea4ec4 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 19 Sep 2022 18:35:08 +0800 Subject: [PATCH] [doc]update api docs (#2406) * update apt docs, test=doc --- docs/source/api/paddlespeech.audio.rst | 3 + ...ddlespeech.audio.streamdata.autodecode.rst | 7 + .../paddlespeech.audio.streamdata.cache.rst | 7 + .../paddlespeech.audio.streamdata.compat.rst | 7 + ...espeech.audio.streamdata.extradatasets.rst | 7 + .../paddlespeech.audio.streamdata.filters.rst | 7 + .../paddlespeech.audio.streamdata.gopen.rst | 7 + ...paddlespeech.audio.streamdata.handlers.rst | 7 + .../api/paddlespeech.audio.streamdata.mix.rst | 7 + ...lespeech.audio.streamdata.paddle_utils.rst | 7 + ...paddlespeech.audio.streamdata.pipeline.rst | 7 + .../api/paddlespeech.audio.streamdata.rst | 28 ++ ...ddlespeech.audio.streamdata.shardlists.rst | 7 + ...lespeech.audio.streamdata.tariterators.rst | 7 + .../paddlespeech.audio.streamdata.utils.rst | 7 + .../paddlespeech.audio.streamdata.writer.rst | 7 + docs/source/api/paddlespeech.audio.text.rst | 16 + ...addlespeech.audio.text.text_featurizer.rst | 7 + .../api/paddlespeech.audio.text.utility.rst | 7 + ...addlespeech.audio.transform.add_deltas.rst | 7 + ...peech.audio.transform.channel_selector.rst | 7 + .../api/paddlespeech.audio.transform.cmvn.rst | 7 + ...addlespeech.audio.transform.functional.rst | 7 + .../paddlespeech.audio.transform.perturb.rst | 7 + .../api/paddlespeech.audio.transform.rst | 24 ++ ...dlespeech.audio.transform.spec_augment.rst | 7 + ...ddlespeech.audio.transform.spectrogram.rst | 7 + ...ch.audio.transform.transform_interface.rst | 7 + ...espeech.audio.transform.transformation.rst | 7 + .../api/paddlespeech.audio.transform.wpe.rst | 7 + .../paddlespeech.audio.utils.check_kwargs.rst | 7 + ...addlespeech.audio.utils.dynamic_import.rst | 7 + docs/source/api/paddlespeech.audio.utils.rst | 3 + .../paddlespeech.audio.utils.tensor_utils.rst | 7 + .../paddlespeech.kws.exps.mdtc.collate.rst | 7 + ...paddlespeech.kws.exps.mdtc.compute_det.rst | 7 + ...dlespeech.kws.exps.mdtc.plot_det_curve.rst | 7 + .../source/api/paddlespeech.kws.exps.mdtc.rst | 19 ++ .../api/paddlespeech.kws.exps.mdtc.score.rst | 7 + .../api/paddlespeech.kws.exps.mdtc.train.rst | 7 + docs/source/api/paddlespeech.kws.exps.rst | 15 + docs/source/api/paddlespeech.kws.rst | 1 + .../api/paddlespeech.resource.model_alias.rst | 7 + ...addlespeech.resource.pretrained_models.rst | 7 + .../api/paddlespeech.resource.resource.rst | 7 + docs/source/api/paddlespeech.resource.rst | 17 + docs/source/api/paddlespeech.rst | 2 + docs/source/api/paddlespeech.s2t.rst | 1 - docs/source/api/paddlespeech.server.utils.rst | 1 - docs/source/api/paddlespeech.t2s.datasets.rst | 1 + .../api/paddlespeech.t2s.datasets.sampler.rst | 7 + .../paddlespeech.t2s.exps.ernie_sat.align.rst | 7 + ...dlespeech.t2s.exps.ernie_sat.normalize.rst | 7 + ...lespeech.t2s.exps.ernie_sat.preprocess.rst | 7 + .../api/paddlespeech.t2s.exps.ernie_sat.rst | 21 ++ ...lespeech.t2s.exps.ernie_sat.synthesize.rst | 7 + ...eech.t2s.exps.ernie_sat.synthesize_e2e.rst | 7 + .../paddlespeech.t2s.exps.ernie_sat.train.rst | 7 + .../paddlespeech.t2s.exps.ernie_sat.utils.rst | 7 + .../api/paddlespeech.t2s.exps.fastspeech2.rst | 1 + ...espeech.t2s.exps.fastspeech2.vc2_infer.rst | 7 + docs/source/api/paddlespeech.t2s.exps.rst | 3 + .../paddlespeech.t2s.exps.stream_play_tts.rst | 7 + .../paddlespeech.t2s.exps.vits.normalize.rst | 7 + .../paddlespeech.t2s.exps.vits.preprocess.rst | 7 + .../source/api/paddlespeech.t2s.exps.vits.rst | 20 ++ .../paddlespeech.t2s.exps.vits.synthesize.rst | 7 + ...dlespeech.t2s.exps.vits.synthesize_e2e.rst | 7 + .../api/paddlespeech.t2s.exps.vits.train.rst | 7 + ...ddlespeech.t2s.exps.vits.voice_cloning.rst | 7 + ...paddlespeech.t2s.frontend.g2pw.dataset.rst | 7 + ...addlespeech.t2s.frontend.g2pw.onnx_api.rst | 7 + .../api/paddlespeech.t2s.frontend.g2pw.rst | 17 + .../paddlespeech.t2s.frontend.g2pw.utils.rst | 7 + ...paddlespeech.t2s.frontend.mix_frontend.rst | 7 + docs/source/api/paddlespeech.t2s.frontend.rst | 2 + ...espeech.t2s.models.ernie_sat.ernie_sat.rst | 7 + ...t2s.models.ernie_sat.ernie_sat_updater.rst | 7 + .../api/paddlespeech.t2s.models.ernie_sat.rst | 3 +- ...h.t2s.models.vits.monotonic_align.core.rst | 7 + ...speech.t2s.models.vits.monotonic_align.rst | 16 + ....t2s.models.vits.monotonic_align.setup.rst | 7 + .../api/paddlespeech.utils.dynamic_import.rst | 7 + docs/source/api/paddlespeech.utils.env.rst | 7 + docs/source/api/paddlespeech.utils.rst | 16 + docs/source/index.rst | 2 + .../t2s/models/ernie_sat/ernie_sat.py | 108 ++++--- .../t2s/models/vits/duration_predictor.py | 39 ++- paddlespeech/t2s/models/vits/flow.py | 111 ++++--- paddlespeech/t2s/models/vits/generator.py | 301 +++++++++++------- .../t2s/models/vits/posterior_encoder.py | 54 ++-- .../t2s/models/vits/residual_coupling.py | 99 ++++-- paddlespeech/t2s/models/vits/text_encoder.py | 69 ++-- paddlespeech/t2s/models/vits/vits.py | 153 ++++++--- .../t2s/models/vits/wavenet/residual_block.py | 24 +- .../t2s/models/vits/wavenet/wavenet.py | 72 +++-- paddlespeech/t2s/models/wavernn/wavernn.py | 20 +- 97 files changed, 1348 insertions(+), 375 deletions(-) create mode 100644 docs/source/api/paddlespeech.audio.streamdata.autodecode.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.cache.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.compat.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.extradatasets.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.filters.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.gopen.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.handlers.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.mix.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.paddle_utils.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.pipeline.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.shardlists.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.tariterators.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.utils.rst create mode 100644 docs/source/api/paddlespeech.audio.streamdata.writer.rst create mode 100644 docs/source/api/paddlespeech.audio.text.rst create mode 100644 docs/source/api/paddlespeech.audio.text.text_featurizer.rst create mode 100644 docs/source/api/paddlespeech.audio.text.utility.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.add_deltas.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.channel_selector.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.cmvn.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.functional.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.perturb.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.spec_augment.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.spectrogram.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.transform_interface.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.transformation.rst create mode 100644 docs/source/api/paddlespeech.audio.transform.wpe.rst create mode 100644 docs/source/api/paddlespeech.audio.utils.check_kwargs.rst create mode 100644 docs/source/api/paddlespeech.audio.utils.dynamic_import.rst create mode 100644 docs/source/api/paddlespeech.audio.utils.tensor_utils.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.mdtc.collate.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.mdtc.compute_det.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.mdtc.plot_det_curve.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.mdtc.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.mdtc.score.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.mdtc.train.rst create mode 100644 docs/source/api/paddlespeech.kws.exps.rst create mode 100644 docs/source/api/paddlespeech.resource.model_alias.rst create mode 100644 docs/source/api/paddlespeech.resource.pretrained_models.rst create mode 100644 docs/source/api/paddlespeech.resource.resource.rst create mode 100644 docs/source/api/paddlespeech.resource.rst create mode 100644 docs/source/api/paddlespeech.t2s.datasets.sampler.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.align.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.normalize.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.preprocess.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize_e2e.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.train.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.ernie_sat.utils.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.fastspeech2.vc2_infer.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.stream_play_tts.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.normalize.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.preprocess.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.synthesize.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.synthesize_e2e.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.train.rst create mode 100644 docs/source/api/paddlespeech.t2s.exps.vits.voice_cloning.rst create mode 100644 docs/source/api/paddlespeech.t2s.frontend.g2pw.dataset.rst create mode 100644 docs/source/api/paddlespeech.t2s.frontend.g2pw.onnx_api.rst create mode 100644 docs/source/api/paddlespeech.t2s.frontend.g2pw.rst create mode 100644 docs/source/api/paddlespeech.t2s.frontend.g2pw.utils.rst create mode 100644 docs/source/api/paddlespeech.t2s.frontend.mix_frontend.rst create mode 100644 docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat.rst create mode 100644 docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat_updater.rst create mode 100644 docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.core.rst create mode 100644 docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.rst create mode 100644 docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.setup.rst create mode 100644 docs/source/api/paddlespeech.utils.dynamic_import.rst create mode 100644 docs/source/api/paddlespeech.utils.env.rst create mode 100644 docs/source/api/paddlespeech.utils.rst diff --git a/docs/source/api/paddlespeech.audio.rst b/docs/source/api/paddlespeech.audio.rst index 5a3867f9620..4ed7e4672cf 100644 --- a/docs/source/api/paddlespeech.audio.rst +++ b/docs/source/api/paddlespeech.audio.rst @@ -20,4 +20,7 @@ Subpackages paddlespeech.audio.io paddlespeech.audio.metric paddlespeech.audio.sox_effects + paddlespeech.audio.streamdata + paddlespeech.audio.text + paddlespeech.audio.transform paddlespeech.audio.utils diff --git a/docs/source/api/paddlespeech.audio.streamdata.autodecode.rst b/docs/source/api/paddlespeech.audio.streamdata.autodecode.rst new file mode 100644 index 00000000000..1e45c13735c --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.autodecode.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.autodecode module +=============================================== + +.. automodule:: paddlespeech.audio.streamdata.autodecode + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.cache.rst b/docs/source/api/paddlespeech.audio.streamdata.cache.rst new file mode 100644 index 00000000000..393055e5475 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.cache.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.cache module +========================================== + +.. automodule:: paddlespeech.audio.streamdata.cache + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.compat.rst b/docs/source/api/paddlespeech.audio.streamdata.compat.rst new file mode 100644 index 00000000000..760695b20d4 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.compat.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.compat module +=========================================== + +.. automodule:: paddlespeech.audio.streamdata.compat + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.extradatasets.rst b/docs/source/api/paddlespeech.audio.streamdata.extradatasets.rst new file mode 100644 index 00000000000..74628e9630d --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.extradatasets.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.extradatasets module +================================================== + +.. automodule:: paddlespeech.audio.streamdata.extradatasets + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.filters.rst b/docs/source/api/paddlespeech.audio.streamdata.filters.rst new file mode 100644 index 00000000000..d26104279bc --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.filters.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.filters module +============================================ + +.. automodule:: paddlespeech.audio.streamdata.filters + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.gopen.rst b/docs/source/api/paddlespeech.audio.streamdata.gopen.rst new file mode 100644 index 00000000000..1cccb776376 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.gopen.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.gopen module +========================================== + +.. automodule:: paddlespeech.audio.streamdata.gopen + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.handlers.rst b/docs/source/api/paddlespeech.audio.streamdata.handlers.rst new file mode 100644 index 00000000000..7a4b3ce8e7c --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.handlers.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.handlers module +============================================= + +.. automodule:: paddlespeech.audio.streamdata.handlers + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.mix.rst b/docs/source/api/paddlespeech.audio.streamdata.mix.rst new file mode 100644 index 00000000000..908b35dd118 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.mix.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.mix module +======================================== + +.. automodule:: paddlespeech.audio.streamdata.mix + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.paddle_utils.rst b/docs/source/api/paddlespeech.audio.streamdata.paddle_utils.rst new file mode 100644 index 00000000000..2033430041b --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.paddle_utils.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.paddle\_utils module +================================================== + +.. automodule:: paddlespeech.audio.streamdata.paddle_utils + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.pipeline.rst b/docs/source/api/paddlespeech.audio.streamdata.pipeline.rst new file mode 100644 index 00000000000..ae05fbecc2e --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.pipeline.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.pipeline module +============================================= + +.. automodule:: paddlespeech.audio.streamdata.pipeline + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.rst b/docs/source/api/paddlespeech.audio.streamdata.rst new file mode 100644 index 00000000000..a1f4560a306 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.rst @@ -0,0 +1,28 @@ +paddlespeech.audio.streamdata package +===================================== + +.. automodule:: paddlespeech.audio.streamdata + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.audio.streamdata.autodecode + paddlespeech.audio.streamdata.cache + paddlespeech.audio.streamdata.compat + paddlespeech.audio.streamdata.extradatasets + paddlespeech.audio.streamdata.filters + paddlespeech.audio.streamdata.gopen + paddlespeech.audio.streamdata.handlers + paddlespeech.audio.streamdata.mix + paddlespeech.audio.streamdata.paddle_utils + paddlespeech.audio.streamdata.pipeline + paddlespeech.audio.streamdata.shardlists + paddlespeech.audio.streamdata.tariterators + paddlespeech.audio.streamdata.utils + paddlespeech.audio.streamdata.writer diff --git a/docs/source/api/paddlespeech.audio.streamdata.shardlists.rst b/docs/source/api/paddlespeech.audio.streamdata.shardlists.rst new file mode 100644 index 00000000000..ec1fe823619 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.shardlists.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.shardlists module +=============================================== + +.. automodule:: paddlespeech.audio.streamdata.shardlists + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.tariterators.rst b/docs/source/api/paddlespeech.audio.streamdata.tariterators.rst new file mode 100644 index 00000000000..b003b2d42f7 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.tariterators.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.tariterators module +================================================= + +.. automodule:: paddlespeech.audio.streamdata.tariterators + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.utils.rst b/docs/source/api/paddlespeech.audio.streamdata.utils.rst new file mode 100644 index 00000000000..f248b11310c --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.utils.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.utils module +========================================== + +.. automodule:: paddlespeech.audio.streamdata.utils + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.streamdata.writer.rst b/docs/source/api/paddlespeech.audio.streamdata.writer.rst new file mode 100644 index 00000000000..7437241f37d --- /dev/null +++ b/docs/source/api/paddlespeech.audio.streamdata.writer.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.streamdata.writer module +=========================================== + +.. automodule:: paddlespeech.audio.streamdata.writer + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.text.rst b/docs/source/api/paddlespeech.audio.text.rst new file mode 100644 index 00000000000..a2018050a68 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.text.rst @@ -0,0 +1,16 @@ +paddlespeech.audio.text package +=============================== + +.. automodule:: paddlespeech.audio.text + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.audio.text.text_featurizer + paddlespeech.audio.text.utility diff --git a/docs/source/api/paddlespeech.audio.text.text_featurizer.rst b/docs/source/api/paddlespeech.audio.text.text_featurizer.rst new file mode 100644 index 00000000000..1a8262d089b --- /dev/null +++ b/docs/source/api/paddlespeech.audio.text.text_featurizer.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.text.text\_featurizer module +=============================================== + +.. automodule:: paddlespeech.audio.text.text_featurizer + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.text.utility.rst b/docs/source/api/paddlespeech.audio.text.utility.rst new file mode 100644 index 00000000000..90fcb25f60b --- /dev/null +++ b/docs/source/api/paddlespeech.audio.text.utility.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.text.utility module +====================================== + +.. automodule:: paddlespeech.audio.text.utility + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.add_deltas.rst b/docs/source/api/paddlespeech.audio.transform.add_deltas.rst new file mode 100644 index 00000000000..b4b596d6ee0 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.add_deltas.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.add\_deltas module +=============================================== + +.. automodule:: paddlespeech.audio.transform.add_deltas + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.channel_selector.rst b/docs/source/api/paddlespeech.audio.transform.channel_selector.rst new file mode 100644 index 00000000000..4828b590485 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.channel_selector.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.channel\_selector module +===================================================== + +.. automodule:: paddlespeech.audio.transform.channel_selector + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.cmvn.rst b/docs/source/api/paddlespeech.audio.transform.cmvn.rst new file mode 100644 index 00000000000..44655a1e4d6 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.cmvn.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.cmvn module +======================================== + +.. automodule:: paddlespeech.audio.transform.cmvn + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.functional.rst b/docs/source/api/paddlespeech.audio.transform.functional.rst new file mode 100644 index 00000000000..7877d2495ba --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.functional.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.functional module +============================================== + +.. automodule:: paddlespeech.audio.transform.functional + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.perturb.rst b/docs/source/api/paddlespeech.audio.transform.perturb.rst new file mode 100644 index 00000000000..e3615a5d145 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.perturb.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.perturb module +=========================================== + +.. automodule:: paddlespeech.audio.transform.perturb + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.rst b/docs/source/api/paddlespeech.audio.transform.rst new file mode 100644 index 00000000000..47a7303b342 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.rst @@ -0,0 +1,24 @@ +paddlespeech.audio.transform package +==================================== + +.. automodule:: paddlespeech.audio.transform + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.audio.transform.add_deltas + paddlespeech.audio.transform.channel_selector + paddlespeech.audio.transform.cmvn + paddlespeech.audio.transform.functional + paddlespeech.audio.transform.perturb + paddlespeech.audio.transform.spec_augment + paddlespeech.audio.transform.spectrogram + paddlespeech.audio.transform.transform_interface + paddlespeech.audio.transform.transformation + paddlespeech.audio.transform.wpe diff --git a/docs/source/api/paddlespeech.audio.transform.spec_augment.rst b/docs/source/api/paddlespeech.audio.transform.spec_augment.rst new file mode 100644 index 00000000000..f11a322410f --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.spec_augment.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.spec\_augment module +================================================= + +.. automodule:: paddlespeech.audio.transform.spec_augment + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.spectrogram.rst b/docs/source/api/paddlespeech.audio.transform.spectrogram.rst new file mode 100644 index 00000000000..6be0c32eea0 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.spectrogram.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.spectrogram module +=============================================== + +.. automodule:: paddlespeech.audio.transform.spectrogram + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.transform_interface.rst b/docs/source/api/paddlespeech.audio.transform.transform_interface.rst new file mode 100644 index 00000000000..ec8b20857af --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.transform_interface.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.transform\_interface module +======================================================== + +.. automodule:: paddlespeech.audio.transform.transform_interface + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.transformation.rst b/docs/source/api/paddlespeech.audio.transform.transformation.rst new file mode 100644 index 00000000000..94629b9afd6 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.transformation.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.transformation module +================================================== + +.. automodule:: paddlespeech.audio.transform.transformation + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.transform.wpe.rst b/docs/source/api/paddlespeech.audio.transform.wpe.rst new file mode 100644 index 00000000000..85c75811494 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.transform.wpe.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.transform.wpe module +======================================= + +.. automodule:: paddlespeech.audio.transform.wpe + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.utils.check_kwargs.rst b/docs/source/api/paddlespeech.audio.utils.check_kwargs.rst new file mode 100644 index 00000000000..a18f27e65a7 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.utils.check_kwargs.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.utils.check\_kwargs module +============================================= + +.. automodule:: paddlespeech.audio.utils.check_kwargs + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.utils.dynamic_import.rst b/docs/source/api/paddlespeech.audio.utils.dynamic_import.rst new file mode 100644 index 00000000000..5d060ee15c3 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.utils.dynamic_import.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.utils.dynamic\_import module +=============================================== + +.. automodule:: paddlespeech.audio.utils.dynamic_import + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.audio.utils.rst b/docs/source/api/paddlespeech.audio.utils.rst index db15927dad9..217afa8fbc9 100644 --- a/docs/source/api/paddlespeech.audio.utils.rst +++ b/docs/source/api/paddlespeech.audio.utils.rst @@ -12,8 +12,11 @@ Submodules .. toctree:: :maxdepth: 4 + paddlespeech.audio.utils.check_kwargs paddlespeech.audio.utils.download + paddlespeech.audio.utils.dynamic_import paddlespeech.audio.utils.error paddlespeech.audio.utils.log paddlespeech.audio.utils.numeric + paddlespeech.audio.utils.tensor_utils paddlespeech.audio.utils.time diff --git a/docs/source/api/paddlespeech.audio.utils.tensor_utils.rst b/docs/source/api/paddlespeech.audio.utils.tensor_utils.rst new file mode 100644 index 00000000000..93a1f70eb25 --- /dev/null +++ b/docs/source/api/paddlespeech.audio.utils.tensor_utils.rst @@ -0,0 +1,7 @@ +paddlespeech.audio.utils.tensor\_utils module +============================================= + +.. automodule:: paddlespeech.audio.utils.tensor_utils + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.kws.exps.mdtc.collate.rst b/docs/source/api/paddlespeech.kws.exps.mdtc.collate.rst new file mode 100644 index 00000000000..b533e8c42a3 --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.mdtc.collate.rst @@ -0,0 +1,7 @@ +paddlespeech.kws.exps.mdtc.collate module +========================================= + +.. automodule:: paddlespeech.kws.exps.mdtc.collate + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.kws.exps.mdtc.compute_det.rst b/docs/source/api/paddlespeech.kws.exps.mdtc.compute_det.rst new file mode 100644 index 00000000000..45e09455500 --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.mdtc.compute_det.rst @@ -0,0 +1,7 @@ +paddlespeech.kws.exps.mdtc.compute\_det module +============================================== + +.. automodule:: paddlespeech.kws.exps.mdtc.compute_det + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.kws.exps.mdtc.plot_det_curve.rst b/docs/source/api/paddlespeech.kws.exps.mdtc.plot_det_curve.rst new file mode 100644 index 00000000000..46a149b0bf1 --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.mdtc.plot_det_curve.rst @@ -0,0 +1,7 @@ +paddlespeech.kws.exps.mdtc.plot\_det\_curve module +================================================== + +.. automodule:: paddlespeech.kws.exps.mdtc.plot_det_curve + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.kws.exps.mdtc.rst b/docs/source/api/paddlespeech.kws.exps.mdtc.rst new file mode 100644 index 00000000000..f6cad64e353 --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.mdtc.rst @@ -0,0 +1,19 @@ +paddlespeech.kws.exps.mdtc package +================================== + +.. automodule:: paddlespeech.kws.exps.mdtc + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.kws.exps.mdtc.collate + paddlespeech.kws.exps.mdtc.compute_det + paddlespeech.kws.exps.mdtc.plot_det_curve + paddlespeech.kws.exps.mdtc.score + paddlespeech.kws.exps.mdtc.train diff --git a/docs/source/api/paddlespeech.kws.exps.mdtc.score.rst b/docs/source/api/paddlespeech.kws.exps.mdtc.score.rst new file mode 100644 index 00000000000..aa956b4cb2f --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.mdtc.score.rst @@ -0,0 +1,7 @@ +paddlespeech.kws.exps.mdtc.score module +======================================= + +.. automodule:: paddlespeech.kws.exps.mdtc.score + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.kws.exps.mdtc.train.rst b/docs/source/api/paddlespeech.kws.exps.mdtc.train.rst new file mode 100644 index 00000000000..5e4ca401a20 --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.mdtc.train.rst @@ -0,0 +1,7 @@ +paddlespeech.kws.exps.mdtc.train module +======================================= + +.. automodule:: paddlespeech.kws.exps.mdtc.train + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.kws.exps.rst b/docs/source/api/paddlespeech.kws.exps.rst new file mode 100644 index 00000000000..bf10d2c9fff --- /dev/null +++ b/docs/source/api/paddlespeech.kws.exps.rst @@ -0,0 +1,15 @@ +paddlespeech.kws.exps package +============================= + +.. automodule:: paddlespeech.kws.exps + :members: + :undoc-members: + :show-inheritance: + +Subpackages +----------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.kws.exps.mdtc diff --git a/docs/source/api/paddlespeech.kws.rst b/docs/source/api/paddlespeech.kws.rst index c2829a42eb8..d21d094c711 100644 --- a/docs/source/api/paddlespeech.kws.rst +++ b/docs/source/api/paddlespeech.kws.rst @@ -12,4 +12,5 @@ Subpackages .. toctree:: :maxdepth: 4 + paddlespeech.kws.exps paddlespeech.kws.models diff --git a/docs/source/api/paddlespeech.resource.model_alias.rst b/docs/source/api/paddlespeech.resource.model_alias.rst new file mode 100644 index 00000000000..b78e643acea --- /dev/null +++ b/docs/source/api/paddlespeech.resource.model_alias.rst @@ -0,0 +1,7 @@ +paddlespeech.resource.model\_alias module +========================================= + +.. automodule:: paddlespeech.resource.model_alias + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.resource.pretrained_models.rst b/docs/source/api/paddlespeech.resource.pretrained_models.rst new file mode 100644 index 00000000000..a020616933b --- /dev/null +++ b/docs/source/api/paddlespeech.resource.pretrained_models.rst @@ -0,0 +1,7 @@ +paddlespeech.resource.pretrained\_models module +=============================================== + +.. automodule:: paddlespeech.resource.pretrained_models + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.resource.resource.rst b/docs/source/api/paddlespeech.resource.resource.rst new file mode 100644 index 00000000000..8b51eda3c22 --- /dev/null +++ b/docs/source/api/paddlespeech.resource.resource.rst @@ -0,0 +1,7 @@ +paddlespeech.resource.resource module +===================================== + +.. automodule:: paddlespeech.resource.resource + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.resource.rst b/docs/source/api/paddlespeech.resource.rst new file mode 100644 index 00000000000..61fdd531785 --- /dev/null +++ b/docs/source/api/paddlespeech.resource.rst @@ -0,0 +1,17 @@ +paddlespeech.resource package +============================= + +.. automodule:: paddlespeech.resource + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.resource.model_alias + paddlespeech.resource.pretrained_models + paddlespeech.resource.resource diff --git a/docs/source/api/paddlespeech.rst b/docs/source/api/paddlespeech.rst index e7a01bf7653..d06cd2c770d 100644 --- a/docs/source/api/paddlespeech.rst +++ b/docs/source/api/paddlespeech.rst @@ -16,8 +16,10 @@ Subpackages paddlespeech.cli paddlespeech.cls paddlespeech.kws + paddlespeech.resource paddlespeech.s2t paddlespeech.server paddlespeech.t2s paddlespeech.text + paddlespeech.utils paddlespeech.vector diff --git a/docs/source/api/paddlespeech.s2t.rst b/docs/source/api/paddlespeech.s2t.rst index 4be22cb878d..be9ef52f553 100644 --- a/docs/source/api/paddlespeech.s2t.rst +++ b/docs/source/api/paddlespeech.s2t.rst @@ -19,5 +19,4 @@ Subpackages paddlespeech.s2t.models paddlespeech.s2t.modules paddlespeech.s2t.training - paddlespeech.s2t.transform paddlespeech.s2t.utils diff --git a/docs/source/api/paddlespeech.server.utils.rst b/docs/source/api/paddlespeech.server.utils.rst index 9d1166392f8..b4051aee34d 100644 --- a/docs/source/api/paddlespeech.server.utils.rst +++ b/docs/source/api/paddlespeech.server.utils.rst @@ -18,7 +18,6 @@ Submodules paddlespeech.server.utils.config paddlespeech.server.utils.errors paddlespeech.server.utils.exception - paddlespeech.server.utils.log paddlespeech.server.utils.onnx_infer paddlespeech.server.utils.paddle_predictor paddlespeech.server.utils.util diff --git a/docs/source/api/paddlespeech.t2s.datasets.rst b/docs/source/api/paddlespeech.t2s.datasets.rst index b40eb2bf19c..dfbdb0b47ca 100644 --- a/docs/source/api/paddlespeech.t2s.datasets.rst +++ b/docs/source/api/paddlespeech.t2s.datasets.rst @@ -19,4 +19,5 @@ Submodules paddlespeech.t2s.datasets.get_feats paddlespeech.t2s.datasets.ljspeech paddlespeech.t2s.datasets.preprocess_utils + paddlespeech.t2s.datasets.sampler paddlespeech.t2s.datasets.vocoder_batch_fn diff --git a/docs/source/api/paddlespeech.t2s.datasets.sampler.rst b/docs/source/api/paddlespeech.t2s.datasets.sampler.rst new file mode 100644 index 00000000000..ed29c28d73b --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.datasets.sampler.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.datasets.sampler module +======================================== + +.. automodule:: paddlespeech.t2s.datasets.sampler + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.align.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.align.rst new file mode 100644 index 00000000000..a5e07aace39 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.align.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.align module +============================================= + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.align + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.normalize.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.normalize.rst new file mode 100644 index 00000000000..3771311cb8c --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.normalize.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.normalize module +================================================= + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.normalize + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.preprocess.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.preprocess.rst new file mode 100644 index 00000000000..8d4c24ffe58 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.preprocess.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.preprocess module +================================================== + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.preprocess + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.rst new file mode 100644 index 00000000000..a611584205d --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.rst @@ -0,0 +1,21 @@ +paddlespeech.t2s.exps.ernie\_sat package +======================================== + +.. automodule:: paddlespeech.t2s.exps.ernie_sat + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.t2s.exps.ernie_sat.align + paddlespeech.t2s.exps.ernie_sat.normalize + paddlespeech.t2s.exps.ernie_sat.preprocess + paddlespeech.t2s.exps.ernie_sat.synthesize + paddlespeech.t2s.exps.ernie_sat.synthesize_e2e + paddlespeech.t2s.exps.ernie_sat.train + paddlespeech.t2s.exps.ernie_sat.utils diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize.rst new file mode 100644 index 00000000000..ecda2a51346 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.synthesize module +================================================== + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.synthesize + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize_e2e.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize_e2e.rst new file mode 100644 index 00000000000..00fc4495266 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.synthesize_e2e.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.synthesize\_e2e module +======================================================= + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.synthesize_e2e + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.train.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.train.rst new file mode 100644 index 00000000000..ba9a3334493 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.train.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.train module +============================================= + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.train + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.ernie_sat.utils.rst b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.utils.rst new file mode 100644 index 00000000000..a2dd26c38fc --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.ernie_sat.utils.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.ernie\_sat.utils module +============================================= + +.. automodule:: paddlespeech.t2s.exps.ernie_sat.utils + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.fastspeech2.rst b/docs/source/api/paddlespeech.t2s.exps.fastspeech2.rst index 3c98aa88256..fad1fd87f7d 100644 --- a/docs/source/api/paddlespeech.t2s.exps.fastspeech2.rst +++ b/docs/source/api/paddlespeech.t2s.exps.fastspeech2.rst @@ -16,3 +16,4 @@ Submodules paddlespeech.t2s.exps.fastspeech2.normalize paddlespeech.t2s.exps.fastspeech2.preprocess paddlespeech.t2s.exps.fastspeech2.train + paddlespeech.t2s.exps.fastspeech2.vc2_infer diff --git a/docs/source/api/paddlespeech.t2s.exps.fastspeech2.vc2_infer.rst b/docs/source/api/paddlespeech.t2s.exps.fastspeech2.vc2_infer.rst new file mode 100644 index 00000000000..70a9d6e1571 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.fastspeech2.vc2_infer.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.fastspeech2.vc2\_infer module +=================================================== + +.. automodule:: paddlespeech.t2s.exps.fastspeech2.vc2_infer + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.rst b/docs/source/api/paddlespeech.t2s.exps.rst index a688435eba0..bee18a97209 100644 --- a/docs/source/api/paddlespeech.t2s.exps.rst +++ b/docs/source/api/paddlespeech.t2s.exps.rst @@ -12,11 +12,13 @@ Subpackages .. toctree:: :maxdepth: 4 + paddlespeech.t2s.exps.ernie_sat paddlespeech.t2s.exps.fastspeech2 paddlespeech.t2s.exps.gan_vocoder paddlespeech.t2s.exps.speedyspeech paddlespeech.t2s.exps.tacotron2 paddlespeech.t2s.exps.transformer_tts + paddlespeech.t2s.exps.vits paddlespeech.t2s.exps.waveflow paddlespeech.t2s.exps.wavernn @@ -31,6 +33,7 @@ Submodules paddlespeech.t2s.exps.ort_predict paddlespeech.t2s.exps.ort_predict_e2e paddlespeech.t2s.exps.ort_predict_streaming + paddlespeech.t2s.exps.stream_play_tts paddlespeech.t2s.exps.syn_utils paddlespeech.t2s.exps.synthesize paddlespeech.t2s.exps.synthesize_e2e diff --git a/docs/source/api/paddlespeech.t2s.exps.stream_play_tts.rst b/docs/source/api/paddlespeech.t2s.exps.stream_play_tts.rst new file mode 100644 index 00000000000..cb22dde0c38 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.stream_play_tts.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.stream\_play\_tts module +============================================== + +.. automodule:: paddlespeech.t2s.exps.stream_play_tts + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.normalize.rst b/docs/source/api/paddlespeech.t2s.exps.vits.normalize.rst new file mode 100644 index 00000000000..c5606f99830 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.normalize.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.vits.normalize module +=========================================== + +.. automodule:: paddlespeech.t2s.exps.vits.normalize + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.preprocess.rst b/docs/source/api/paddlespeech.t2s.exps.vits.preprocess.rst new file mode 100644 index 00000000000..50633c621ee --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.preprocess.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.vits.preprocess module +============================================ + +.. automodule:: paddlespeech.t2s.exps.vits.preprocess + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.rst b/docs/source/api/paddlespeech.t2s.exps.vits.rst new file mode 100644 index 00000000000..51a9418d598 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.rst @@ -0,0 +1,20 @@ +paddlespeech.t2s.exps.vits package +================================== + +.. automodule:: paddlespeech.t2s.exps.vits + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.t2s.exps.vits.normalize + paddlespeech.t2s.exps.vits.preprocess + paddlespeech.t2s.exps.vits.synthesize + paddlespeech.t2s.exps.vits.synthesize_e2e + paddlespeech.t2s.exps.vits.train + paddlespeech.t2s.exps.vits.voice_cloning diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.synthesize.rst b/docs/source/api/paddlespeech.t2s.exps.vits.synthesize.rst new file mode 100644 index 00000000000..4b22d069a5f --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.synthesize.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.vits.synthesize module +============================================ + +.. automodule:: paddlespeech.t2s.exps.vits.synthesize + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.synthesize_e2e.rst b/docs/source/api/paddlespeech.t2s.exps.vits.synthesize_e2e.rst new file mode 100644 index 00000000000..053ddfc8328 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.synthesize_e2e.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.vits.synthesize\_e2e module +================================================= + +.. automodule:: paddlespeech.t2s.exps.vits.synthesize_e2e + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.train.rst b/docs/source/api/paddlespeech.t2s.exps.vits.train.rst new file mode 100644 index 00000000000..31bd3a48f58 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.train.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.vits.train module +======================================= + +.. automodule:: paddlespeech.t2s.exps.vits.train + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.exps.vits.voice_cloning.rst b/docs/source/api/paddlespeech.t2s.exps.vits.voice_cloning.rst new file mode 100644 index 00000000000..d9be0f310f7 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.exps.vits.voice_cloning.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.exps.vits.voice\_cloning module +================================================ + +.. automodule:: paddlespeech.t2s.exps.vits.voice_cloning + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.frontend.g2pw.dataset.rst b/docs/source/api/paddlespeech.t2s.frontend.g2pw.dataset.rst new file mode 100644 index 00000000000..1635ec284c9 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.frontend.g2pw.dataset.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.frontend.g2pw.dataset module +============================================= + +.. automodule:: paddlespeech.t2s.frontend.g2pw.dataset + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.frontend.g2pw.onnx_api.rst b/docs/source/api/paddlespeech.t2s.frontend.g2pw.onnx_api.rst new file mode 100644 index 00000000000..b7d549070e2 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.frontend.g2pw.onnx_api.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.frontend.g2pw.onnx\_api module +=============================================== + +.. automodule:: paddlespeech.t2s.frontend.g2pw.onnx_api + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.frontend.g2pw.rst b/docs/source/api/paddlespeech.t2s.frontend.g2pw.rst new file mode 100644 index 00000000000..10a118b7650 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.frontend.g2pw.rst @@ -0,0 +1,17 @@ +paddlespeech.t2s.frontend.g2pw package +====================================== + +.. automodule:: paddlespeech.t2s.frontend.g2pw + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.t2s.frontend.g2pw.dataset + paddlespeech.t2s.frontend.g2pw.onnx_api + paddlespeech.t2s.frontend.g2pw.utils diff --git a/docs/source/api/paddlespeech.t2s.frontend.g2pw.utils.rst b/docs/source/api/paddlespeech.t2s.frontend.g2pw.utils.rst new file mode 100644 index 00000000000..ce942803792 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.frontend.g2pw.utils.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.frontend.g2pw.utils module +=========================================== + +.. automodule:: paddlespeech.t2s.frontend.g2pw.utils + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.frontend.mix_frontend.rst b/docs/source/api/paddlespeech.t2s.frontend.mix_frontend.rst new file mode 100644 index 00000000000..4505dddba61 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.frontend.mix_frontend.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.frontend.mix\_frontend module +============================================== + +.. automodule:: paddlespeech.t2s.frontend.mix_frontend + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.frontend.rst b/docs/source/api/paddlespeech.t2s.frontend.rst index 8fbf1e6ebc5..b6106861629 100644 --- a/docs/source/api/paddlespeech.t2s.frontend.rst +++ b/docs/source/api/paddlespeech.t2s.frontend.rst @@ -12,6 +12,7 @@ Subpackages .. toctree:: :maxdepth: 4 + paddlespeech.t2s.frontend.g2pw paddlespeech.t2s.frontend.normalizer paddlespeech.t2s.frontend.zh_normalization @@ -23,6 +24,7 @@ Submodules paddlespeech.t2s.frontend.arpabet paddlespeech.t2s.frontend.generate_lexicon + paddlespeech.t2s.frontend.mix_frontend paddlespeech.t2s.frontend.phonectic paddlespeech.t2s.frontend.punctuation paddlespeech.t2s.frontend.tone_sandhi diff --git a/docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat.rst b/docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat.rst new file mode 100644 index 00000000000..fce5a83cc58 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.models.ernie\_sat.ernie\_sat module +==================================================== + +.. automodule:: paddlespeech.t2s.models.ernie_sat.ernie_sat + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat_updater.rst b/docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat_updater.rst new file mode 100644 index 00000000000..8a697d6cf35 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.models.ernie_sat.ernie_sat_updater.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.models.ernie\_sat.ernie\_sat\_updater module +============================================================= + +.. automodule:: paddlespeech.t2s.models.ernie_sat.ernie_sat_updater + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.models.ernie_sat.rst b/docs/source/api/paddlespeech.t2s.models.ernie_sat.rst index 680a85deaf2..aff7489c736 100644 --- a/docs/source/api/paddlespeech.t2s.models.ernie_sat.rst +++ b/docs/source/api/paddlespeech.t2s.models.ernie_sat.rst @@ -12,4 +12,5 @@ Submodules .. toctree:: :maxdepth: 4 - paddlespeech.t2s.models.ernie_sat.mlm + paddlespeech.t2s.models.ernie_sat.ernie_sat + paddlespeech.t2s.models.ernie_sat.ernie_sat_updater diff --git a/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.core.rst b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.core.rst new file mode 100644 index 00000000000..7aaba795299 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.core.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.models.vits.monotonic\_align.core module +========================================================= + +.. automodule:: paddlespeech.t2s.models.vits.monotonic_align.core + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.rst b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.rst new file mode 100644 index 00000000000..25c819a7efd --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.rst @@ -0,0 +1,16 @@ +paddlespeech.t2s.models.vits.monotonic\_align package +===================================================== + +.. automodule:: paddlespeech.t2s.models.vits.monotonic_align + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.t2s.models.vits.monotonic_align.core + paddlespeech.t2s.models.vits.monotonic_align.setup diff --git a/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.setup.rst b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.setup.rst new file mode 100644 index 00000000000..a93c3b8bf62 --- /dev/null +++ b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.setup.rst @@ -0,0 +1,7 @@ +paddlespeech.t2s.models.vits.monotonic\_align.setup module +========================================================== + +.. automodule:: paddlespeech.t2s.models.vits.monotonic_align.setup + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.utils.dynamic_import.rst b/docs/source/api/paddlespeech.utils.dynamic_import.rst new file mode 100644 index 00000000000..daa4e6e7845 --- /dev/null +++ b/docs/source/api/paddlespeech.utils.dynamic_import.rst @@ -0,0 +1,7 @@ +paddlespeech.utils.dynamic\_import module +========================================= + +.. automodule:: paddlespeech.utils.dynamic_import + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.utils.env.rst b/docs/source/api/paddlespeech.utils.env.rst new file mode 100644 index 00000000000..e51278f8288 --- /dev/null +++ b/docs/source/api/paddlespeech.utils.env.rst @@ -0,0 +1,7 @@ +paddlespeech.utils.env module +============================= + +.. automodule:: paddlespeech.utils.env + :members: + :undoc-members: + :show-inheritance: diff --git a/docs/source/api/paddlespeech.utils.rst b/docs/source/api/paddlespeech.utils.rst new file mode 100644 index 00000000000..3d47626bbdc --- /dev/null +++ b/docs/source/api/paddlespeech.utils.rst @@ -0,0 +1,16 @@ +paddlespeech.utils package +========================== + +.. automodule:: paddlespeech.utils + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + paddlespeech.utils.dynamic_import + paddlespeech.utils.env diff --git a/docs/source/index.rst b/docs/source/index.rst index 83474c5286d..8540d3fc67a 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -74,8 +74,10 @@ Contents paddlespeech.cli paddlespeech.cls paddlespeech.kws + paddlespeech.resource paddlespeech.s2t paddlespeech.server paddlespeech.t2s paddlespeech.text + paddlespeech.utils paddlespeech.vector diff --git a/paddlespeech/t2s/models/ernie_sat/ernie_sat.py b/paddlespeech/t2s/models/ernie_sat/ernie_sat.py index 08c43dc5f8d..eb42b33ed39 100644 --- a/paddlespeech/t2s/models/ernie_sat/ernie_sat.py +++ b/paddlespeech/t2s/models/ernie_sat/ernie_sat.py @@ -71,31 +71,53 @@ class MLMEncoder(nn.Layer): """Conformer encoder module. Args: - idim (int): Input dimension. - attention_dim (int): Dimension of attention. - attention_heads (int): The number of heads of multi head attention. - linear_units (int): The number of units of position-wise feed forward. - num_blocks (int): The number of decoder blocks. - dropout_rate (float): Dropout rate. - positional_dropout_rate (float): Dropout rate after adding positional encoding. - attention_dropout_rate (float): Dropout rate in attention. - input_layer (Union[str, paddle.nn.Layer]): Input layer type. - normalize_before (bool): Whether to use layer_norm before the first block. - concat_after (bool): Whether to concat attention layer's input and output. + idim (int): + Input dimension. + attention_dim (int): + Dimension of attention. + attention_heads (int): + The number of heads of multi head attention. + linear_units (int): + The number of units of position-wise feed forward. + num_blocks (int): + The number of decoder blocks. + dropout_rate (float): + Dropout rate. + positional_dropout_rate (float): + Dropout rate after adding positional encoding. + attention_dropout_rate (float): + Dropout rate in attention. + input_layer (Union[str, paddle.nn.Layer]): + Input layer type. + normalize_before (bool): + Whether to use layer_norm before the first block. + concat_after (bool): + Whether to concat attention layer's input and output. if True, additional linear will be applied. i.e. x -> x + linear(concat(x, att(x))) if False, no additional linear will be applied. i.e. x -> x + att(x) - positionwise_layer_type (str): "linear", "conv1d", or "conv1d-linear". - positionwise_conv_kernel_size (int): Kernel size of positionwise conv1d layer. - macaron_style (bool): Whether to use macaron style for positionwise layer. - pos_enc_layer_type (str): Encoder positional encoding layer type. - selfattention_layer_type (str): Encoder attention layer type. - activation_type (str): Encoder activation function type. - use_cnn_module (bool): Whether to use convolution module. - zero_triu (bool): Whether to zero the upper triangular part of attention matrix. - cnn_module_kernel (int): Kernerl size of convolution module. - padding_idx (int): Padding idx for input_layer=embed. - stochastic_depth_rate (float): Maximum probability to skip the encoder layer. + positionwise_layer_type (str): + "linear", "conv1d", or "conv1d-linear". + positionwise_conv_kernel_size (int): + Kernel size of positionwise conv1d layer. + macaron_style (bool): + Whether to use macaron style for positionwise layer. + pos_enc_layer_type (str): + Encoder positional encoding layer type. + selfattention_layer_type (str): + Encoder attention layer type. + activation_type (str): + Encoder activation function type. + use_cnn_module (bool): + Whether to use convolution module. + zero_triu (bool): + Whether to zero the upper triangular part of attention matrix. + cnn_module_kernel (int): + Kernerl size of convolution module. + padding_idx (int): + Padding idx for input_layer=embed. + stochastic_depth_rate (float): + Maximum probability to skip the encoder layer. """ @@ -320,12 +342,16 @@ def forward(self, xs: paddle.Tensor, masks: paddle.Tensor): """Encode input sequence. Args: - xs (paddle.Tensor): Input tensor (#batch, time, idim). - masks (paddle.Tensor): Mask tensor (#batch, time). + xs (paddle.Tensor): + Input tensor (#batch, time, idim). + masks (paddle.Tensor): + Mask tensor (#batch, time). Returns: - paddle.Tensor: Output tensor (#batch, time, attention_dim). - paddle.Tensor: Mask tensor (#batch, time). + paddle.Tensor: + Output tensor (#batch, time, attention_dim). + paddle.Tensor: + Mask tensor (#batch, time). """ xs = self.embed(xs) @@ -392,19 +418,27 @@ def inference( use_teacher_forcing: bool=True, ) -> List[paddle.Tensor]: ''' Args: - speech (paddle.Tensor): input speech (1, Tmax, D). - text (paddle.Tensor): input text (1, Tmax2). - masked_pos (paddle.Tensor): masked position of input speech (1, Tmax) - speech_mask (paddle.Tensor): mask of speech (1, 1, Tmax). - text_mask (paddle.Tensor): mask of text (1, 1, Tmax2). - speech_seg_pos (paddle.Tensor): n-th phone of each mel, 0<=n<=Tmax2 (1, Tmax). - text_seg_pos (paddle.Tensor): n-th phone of each phone, 0<=n<=Tmax2 (1, Tmax2). - span_bdy (List[int]): masked mel boundary of input speech (2,) - use_teacher_forcing (bool): whether to use teacher forcing + speech (paddle.Tensor): + input speech (1, Tmax, D). + text (paddle.Tensor): + input text (1, Tmax2). + masked_pos (paddle.Tensor): + masked position of input speech (1, Tmax) + speech_mask (paddle.Tensor): + mask of speech (1, 1, Tmax). + text_mask (paddle.Tensor): + mask of text (1, 1, Tmax2). + speech_seg_pos (paddle.Tensor): + n-th phone of each mel, 0<=n<=Tmax2 (1, Tmax). + text_seg_pos (paddle.Tensor): + n-th phone of each phone, 0<=n<=Tmax2 (1, Tmax2). + span_bdy (List[int]): + masked mel boundary of input speech (2,) + use_teacher_forcing (bool): + whether to use teacher forcing Returns: List[Tensor]: - eg: - [Tensor(shape=[1, 181, 80]), Tensor(shape=[80, 80]), Tensor(shape=[1, 67, 80])] + eg: [Tensor(shape=[1, 181, 80]), Tensor(shape=[80, 80]), Tensor(shape=[1, 67, 80])] ''' z_cache = None diff --git a/paddlespeech/t2s/models/vits/duration_predictor.py b/paddlespeech/t2s/models/vits/duration_predictor.py index 6197d569637..b0bb68d0f5d 100644 --- a/paddlespeech/t2s/models/vits/duration_predictor.py +++ b/paddlespeech/t2s/models/vits/duration_predictor.py @@ -48,12 +48,18 @@ def __init__( global_channels: int=-1, ): """Initialize StochasticDurationPredictor module. Args: - channels (int): Number of channels. - kernel_size (int): Kernel size. - dropout_rate (float): Dropout rate. - flows (int): Number of flows. - dds_conv_layers (int): Number of conv layers in DDS conv. - global_channels (int): Number of global conditioning channels. + channels (int): + Number of channels. + kernel_size (int): + Kernel size. + dropout_rate (float): + Dropout rate. + flows (int): + Number of flows. + dds_conv_layers (int): + Number of conv layers in DDS conv. + global_channels (int): + Number of global conditioning channels. """ super().__init__() @@ -108,14 +114,21 @@ def forward( noise_scale: float=1.0, ) -> paddle.Tensor: """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, channels, T_text). - x_mask (Tensor): Mask tensor (B, 1, T_text). - w (Optional[Tensor]): Duration tensor (B, 1, T_text). - g (Optional[Tensor]): Global conditioning tensor (B, channels, 1) - inverse (bool): Whether to inverse the flow. - noise_scale (float): Noise scale value. + x (Tensor): + Input tensor (B, channels, T_text). + x_mask (Tensor): + Mask tensor (B, 1, T_text). + w (Optional[Tensor]): + Duration tensor (B, 1, T_text). + g (Optional[Tensor]): + Global conditioning tensor (B, channels, 1) + inverse (bool): + Whether to inverse the flow. + noise_scale (float): + Noise scale value. Returns: - Tensor: If not inverse, negative log-likelihood (NLL) tensor (B,). + Tensor: + If not inverse, negative log-likelihood (NLL) tensor (B,). If inverse, log-duration tensor (B, 1, T_text). """ # stop gradient diff --git a/paddlespeech/t2s/models/vits/flow.py b/paddlespeech/t2s/models/vits/flow.py index 3c8f89356e9..7593eb72733 100644 --- a/paddlespeech/t2s/models/vits/flow.py +++ b/paddlespeech/t2s/models/vits/flow.py @@ -34,11 +34,15 @@ def forward(self, x: paddle.Tensor, *args, inverse: bool=False, **kwargs ) -> Union[paddle.Tensor, Tuple[paddle.Tensor, paddle.Tensor]]: """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, channels, T). - inverse (bool): Whether to inverse the flow. + x (Tensor): + Input tensor (B, channels, T). + inverse (bool): + Whether to inverse the flow. Returns: - Tensor: Flipped tensor (B, channels, T). - Tensor: Log-determinant tensor for NLL (B,) if not inverse. + Tensor: + Flipped tensor (B, channels, T). + Tensor: + Log-determinant tensor for NLL (B,) if not inverse. """ x = paddle.flip(x, [1]) if not inverse: @@ -60,13 +64,19 @@ def forward(self, ) -> Union[paddle.Tensor, Tuple[paddle.Tensor, paddle.Tensor]]: """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, channels, T). - x_mask (Tensor): Mask tensor (B, 1, T). - inverse (bool): Whether to inverse the flow. - eps (float): Epsilon for log. + x (Tensor): + Input tensor (B, channels, T). + x_mask (Tensor): + Mask tensor (B, 1, T). + inverse (bool): + Whether to inverse the flow. + eps (float): + Epsilon for log. Returns: - Tensor: Output tensor (B, channels, T). - Tensor: Log-determinant tensor for NLL (B,) if not inverse. + Tensor: + Output tensor (B, channels, T). + Tensor: + Log-determinant tensor for NLL (B,) if not inverse. """ if not inverse: y = paddle.log(paddle.clip(x, min=eps)) * x_mask @@ -83,7 +93,8 @@ class ElementwiseAffineFlow(nn.Layer): def __init__(self, channels: int): """Initialize ElementwiseAffineFlow module. Args: - channels (int): Number of channels. + channels (int): + Number of channels. """ super().__init__() self.channels = channels @@ -107,12 +118,17 @@ def forward(self, ) -> Union[paddle.Tensor, Tuple[paddle.Tensor, paddle.Tensor]]: """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, channels, T). - x_mask (Tensor): Mask tensor (B, 1, T). - inverse (bool): Whether to inverse the flow. + x (Tensor): + Input tensor (B, channels, T). + x_mask (Tensor): + Mask tensor (B, 1, T). + inverse (bool): + Whether to inverse the flow. Returns: - Tensor: Output tensor (B, channels, T). - Tensor: Log-determinant tensor for NLL (B,) if not inverse. + Tensor: + Output tensor (B, channels, T). + Tensor: + Log-determinant tensor for NLL (B,) if not inverse. """ if not inverse: y = self.m + paddle.exp(self.logs) * x @@ -157,11 +173,16 @@ def __init__( eps: float=1e-5, ): """Initialize DilatedDepthSeparableConv module. Args: - channels (int): Number of channels. - kernel_size (int): Kernel size. - layers (int): Number of layers. - dropout_rate (float): Dropout rate. - eps (float): Epsilon for layer norm. + channels (int): + Number of channels. + kernel_size (int): + Kernel size. + layers (int): + Number of layers. + dropout_rate (float): + Dropout rate. + eps (float): + Epsilon for layer norm. """ super().__init__() @@ -198,11 +219,15 @@ def forward(self, g: Optional[paddle.Tensor]=None) -> paddle.Tensor: """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, in_channels, T). - x_mask (Tensor): Mask tensor (B, 1, T). - g (Optional[Tensor]): Global conditioning tensor (B, global_channels, 1). + x (Tensor): + Input tensor (B, in_channels, T). + x_mask (Tensor): + Mask tensor (B, 1, T). + g (Optional[Tensor]): + Global conditioning tensor (B, global_channels, 1). Returns: - Tensor: Output tensor (B, channels, T). + Tensor: + Output tensor (B, channels, T). """ if g is not None: x = x + g @@ -225,12 +250,18 @@ def __init__( tail_bound: float=5.0, ): """Initialize ConvFlow module. Args: - in_channels (int): Number of input channels. - hidden_channels (int): Number of hidden channels. - kernel_size (int): Kernel size. - layers (int): Number of layers. - bins (int): Number of bins. - tail_bound (float): Tail bound value. + in_channels (int): + Number of input channels. + hidden_channels (int): + Number of hidden channels. + kernel_size (int): + Kernel size. + layers (int): + Number of layers. + bins (int): + Number of bins. + tail_bound (float): + Tail bound value. """ super().__init__() self.half_channels = in_channels // 2 @@ -275,13 +306,19 @@ def forward( ) -> Union[paddle.Tensor, Tuple[paddle.Tensor, paddle.Tensor]]: """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, channels, T). - x_mask (Tensor): Mask tensor (B, 1, T). - g (Optional[Tensor]): Global conditioning tensor (B, channels, 1). - inverse (bool): Whether to inverse the flow. + x (Tensor): + Input tensor (B, channels, T). + x_mask (Tensor): + Mask tensor (B, 1, T). + g (Optional[Tensor]): + Global conditioning tensor (B, channels, 1). + inverse (bool): + Whether to inverse the flow. Returns: - Tensor: Output tensor (B, channels, T). - Tensor: Log-determinant tensor for NLL (B,) if not inverse. + Tensor: + Output tensor (B, channels, T). + Tensor: + Log-determinant tensor for NLL (B,) if not inverse. """ xa, xb = x.split(2, 1) h = self.input_conv(xa) diff --git a/paddlespeech/t2s/models/vits/generator.py b/paddlespeech/t2s/models/vits/generator.py index 359b662586c..7ecc5161972 100644 --- a/paddlespeech/t2s/models/vits/generator.py +++ b/paddlespeech/t2s/models/vits/generator.py @@ -97,81 +97,104 @@ def __init__( stochastic_duration_predictor_dds_conv_layers: int=3, ): """Initialize VITS generator module. Args: - vocabs (int): Input vocabulary size. - aux_channels (int): Number of acoustic feature channels. - hidden_channels (int): Number of hidden channels. - spks (Optional[int]): Number of speakers. If set to > 1, assume that the + vocabs (int): + Input vocabulary size. + aux_channels (int): + Number of acoustic feature channels. + hidden_channels (int): + Number of hidden channels. + spks (Optional[int]): + Number of speakers. If set to > 1, assume that the sids will be provided as the input and use sid embedding layer. - langs (Optional[int]): Number of languages. If set to > 1, assume that the + langs (Optional[int]): + Number of languages. If set to > 1, assume that the lids will be provided as the input and use sid embedding layer. - spk_embed_dim (Optional[int]): Speaker embedding dimension. If set to > 0, + spk_embed_dim (Optional[int]): + Speaker embedding dimension. If set to > 0, assume that spembs will be provided as the input. - global_channels (int): Number of global conditioning channels. - segment_size (int): Segment size for decoder. - text_encoder_attention_heads (int): Number of heads in conformer block - of text encoder. - text_encoder_ffn_expand (int): Expansion ratio of FFN in conformer block - of text encoder. - text_encoder_blocks (int): Number of conformer blocks in text encoder. - text_encoder_positionwise_layer_type (str): Position-wise layer type in - conformer block of text encoder. - text_encoder_positionwise_conv_kernel_size (int): Position-wise convolution - kernel size in conformer block of text encoder. Only used when the - above layer type is conv1d or conv1d-linear. - text_encoder_positional_encoding_layer_type (str): Positional encoding layer - type in conformer block of text encoder. - text_encoder_self_attention_layer_type (str): Self-attention layer type in - conformer block of text encoder. - text_encoder_activation_type (str): Activation function type in conformer - block of text encoder. - text_encoder_normalize_before (bool): Whether to apply layer norm before - self-attention in conformer block of text encoder. - text_encoder_dropout_rate (float): Dropout rate in conformer block of - text encoder. - text_encoder_positional_dropout_rate (float): Dropout rate for positional - encoding in conformer block of text encoder. - text_encoder_attention_dropout_rate (float): Dropout rate for attention in - conformer block of text encoder. - text_encoder_conformer_kernel_size (int): Conformer conv kernel size. It - will be used when only use_conformer_conv_in_text_encoder = True. - use_macaron_style_in_text_encoder (bool): Whether to use macaron style FFN - in conformer block of text encoder. - use_conformer_conv_in_text_encoder (bool): Whether to use covolution in - conformer block of text encoder. - decoder_kernel_size (int): Decoder kernel size. - decoder_channels (int): Number of decoder initial channels. - decoder_upsample_scales (List[int]): List of upsampling scales in decoder. - decoder_upsample_kernel_sizes (List[int]): List of kernel size for - upsampling layers in decoder. - decoder_resblock_kernel_sizes (List[int]): List of kernel size for resblocks - in decoder. - decoder_resblock_dilations (List[List[int]]): List of list of dilations for - resblocks in decoder. - use_weight_norm_in_decoder (bool): Whether to apply weight normalization in - decoder. - posterior_encoder_kernel_size (int): Posterior encoder kernel size. - posterior_encoder_layers (int): Number of layers of posterior encoder. - posterior_encoder_stacks (int): Number of stacks of posterior encoder. - posterior_encoder_base_dilation (int): Base dilation of posterior encoder. - posterior_encoder_dropout_rate (float): Dropout rate for posterior encoder. - use_weight_norm_in_posterior_encoder (bool): Whether to apply weight - normalization in posterior encoder. - flow_flows (int): Number of flows in flow. - flow_kernel_size (int): Kernel size in flow. - flow_base_dilation (int): Base dilation in flow. - flow_layers (int): Number of layers in flow. - flow_dropout_rate (float): Dropout rate in flow - use_weight_norm_in_flow (bool): Whether to apply weight normalization in - flow. - use_only_mean_in_flow (bool): Whether to use only mean in flow. - stochastic_duration_predictor_kernel_size (int): Kernel size in stochastic - duration predictor. - stochastic_duration_predictor_dropout_rate (float): Dropout rate in - stochastic duration predictor. - stochastic_duration_predictor_flows (int): Number of flows in stochastic - duration predictor. - stochastic_duration_predictor_dds_conv_layers (int): Number of DDS conv - layers in stochastic duration predictor. + global_channels (int): + Number of global conditioning channels. + segment_size (int): + Segment size for decoder. + text_encoder_attention_heads (int): + Number of heads in conformer block of text encoder. + text_encoder_ffn_expand (int): + Expansion ratio of FFN in conformer block of text encoder. + text_encoder_blocks (int): + Number of conformer blocks in text encoder. + text_encoder_positionwise_layer_type (str): + Position-wise layer type in conformer block of text encoder. + text_encoder_positionwise_conv_kernel_size (int): + Position-wise convolution kernel size in conformer block of text encoder. + Only used when the above layer type is conv1d or conv1d-linear. + text_encoder_positional_encoding_layer_type (str): + Positional encoding layer type in conformer block of text encoder. + text_encoder_self_attention_layer_type (str): + Self-attention layer type in conformer block of text encoder. + text_encoder_activation_type (str): + Activation function type in conformer block of text encoder. + text_encoder_normalize_before (bool): + Whether to apply layer norm before self-attention in conformer block of text encoder. + text_encoder_dropout_rate (float): + Dropout rate in conformer block of text encoder. + text_encoder_positional_dropout_rate (float): + Dropout rate for positional encoding in conformer block of text encoder. + text_encoder_attention_dropout_rate (float): + Dropout rate for attention in conformer block of text encoder. + text_encoder_conformer_kernel_size (int): + Conformer conv kernel size. It will be used when only use_conformer_conv_in_text_encoder = True. + use_macaron_style_in_text_encoder (bool): + Whether to use macaron style FFN in conformer block of text encoder. + use_conformer_conv_in_text_encoder (bool): + Whether to use covolution in conformer block of text encoder. + decoder_kernel_size (int): + Decoder kernel size. + decoder_channels (int): + Number of decoder initial channels. + decoder_upsample_scales (List[int]): + List of upsampling scales in decoder. + decoder_upsample_kernel_sizes (List[int]): + List of kernel size for upsampling layers in decoder. + decoder_resblock_kernel_sizes (List[int]): + List of kernel size for resblocks in decoder. + decoder_resblock_dilations (List[List[int]]): + List of list of dilations for resblocks in decoder. + use_weight_norm_in_decoder (bool): + Whether to apply weight normalization in decoder. + posterior_encoder_kernel_size (int): + Posterior encoder kernel size. + posterior_encoder_layers (int): + Number of layers of posterior encoder. + posterior_encoder_stacks (int): + Number of stacks of posterior encoder. + posterior_encoder_base_dilation (int): + Base dilation of posterior encoder. + posterior_encoder_dropout_rate (float): + Dropout rate for posterior encoder. + use_weight_norm_in_posterior_encoder (bool): + Whether to apply weight normalization in posterior encoder. + flow_flows (int): + Number of flows in flow. + flow_kernel_size (int): + Kernel size in flow. + flow_base_dilation (int): + Base dilation in flow. + flow_layers (int): + Number of layers in flow. + flow_dropout_rate (float): + Dropout rate in flow + use_weight_norm_in_flow (bool): + Whether to apply weight normalization in flow. + use_only_mean_in_flow (bool): + Whether to use only mean in flow. + stochastic_duration_predictor_kernel_size (int): + Kernel size in stochastic duration predictor. + stochastic_duration_predictor_dropout_rate (float): + Dropout rate in stochastic duration predictor. + stochastic_duration_predictor_flows (int): + Number of flows in stochastic duration predictor. + stochastic_duration_predictor_dds_conv_layers (int): + Number of DDS conv layers in stochastic duration predictor. """ super().__init__() self.segment_size = segment_size @@ -272,27 +295,40 @@ def forward( paddle.Tensor, paddle.Tensor, ], ]: """Calculate forward propagation. Args: - text (Tensor): Text index tensor (B, T_text). - text_lengths (Tensor): Text length tensor (B,). - feats (Tensor): Feature tensor (B, aux_channels, T_feats). - feats_lengths (Tensor): Feature length tensor (B,). - sids (Optional[Tensor]): Speaker index tensor (B,) or (B, 1). - spembs (Optional[Tensor]): Speaker embedding tensor (B, spk_embed_dim). - lids (Optional[Tensor]): Language index tensor (B,) or (B, 1). + text (Tensor): + Text index tensor (B, T_text). + text_lengths (Tensor): + Text length tensor (B,). + feats (Tensor): + Feature tensor (B, aux_channels, T_feats). + feats_lengths (Tensor): + Feature length tensor (B,). + sids (Optional[Tensor]): + Speaker index tensor (B,) or (B, 1). + spembs (Optional[Tensor]): + Speaker embedding tensor (B, spk_embed_dim). + lids (Optional[Tensor]): + Language index tensor (B,) or (B, 1). Returns: - Tensor: Waveform tensor (B, 1, segment_size * upsample_factor). - Tensor: Duration negative log-likelihood (NLL) tensor (B,). - Tensor: Monotonic attention weight tensor (B, 1, T_feats, T_text). - Tensor: Segments start index tensor (B,). - Tensor: Text mask tensor (B, 1, T_text). - Tensor: Feature mask tensor (B, 1, T_feats). - tuple[Tensor, Tensor, Tensor, Tensor, Tensor, Tensor]: - - Tensor: Posterior encoder hidden representation (B, H, T_feats). - - Tensor: Flow hidden representation (B, H, T_feats). - - Tensor: Expanded text encoder projected mean (B, H, T_feats). - - Tensor: Expanded text encoder projected scale (B, H, T_feats). - - Tensor: Posterior encoder projected mean (B, H, T_feats). - - Tensor: Posterior encoder projected scale (B, H, T_feats). + Tensor: + Waveform tensor (B, 1, segment_size * upsample_factor). + Tensor: + Duration negative log-likelihood (NLL) tensor (B,). + Tensor: + Monotonic attention weight tensor (B, 1, T_feats, T_text). + Tensor: + Segments start index tensor (B,). + Tensor: + Text mask tensor (B, 1, T_text). + Tensor: + Feature mask tensor (B, 1, T_feats). + tuple[Tensor, Tensor, Tensor, Tensor, Tensor, Tensor]: + - Tensor: Posterior encoder hidden representation (B, H, T_feats). + - Tensor: Flow hidden representation (B, H, T_feats). + - Tensor: Expanded text encoder projected mean (B, H, T_feats). + - Tensor: Expanded text encoder projected scale (B, H, T_feats). + - Tensor: Posterior encoder projected mean (B, H, T_feats). + - Tensor: Posterior encoder projected scale (B, H, T_feats). """ # forward text encoder x, m_p, logs_p, x_mask = self.text_encoder(text, text_lengths) @@ -402,24 +438,40 @@ def inference( ) -> Tuple[paddle.Tensor, paddle.Tensor, paddle.Tensor]: """Run inference. Args: - text (Tensor): Input text index tensor (B, T_text,). - text_lengths (Tensor): Text length tensor (B,). - feats (Tensor): Feature tensor (B, aux_channels, T_feats,). - feats_lengths (Tensor): Feature length tensor (B,). - sids (Optional[Tensor]): Speaker index tensor (B,) or (B, 1). - spembs (Optional[Tensor]): Speaker embedding tensor (B, spk_embed_dim). - lids (Optional[Tensor]): Language index tensor (B,) or (B, 1). - dur (Optional[Tensor]): Ground-truth duration (B, T_text,). If provided, + text (Tensor): + Input text index tensor (B, T_text,). + text_lengths (Tensor): + Text length tensor (B,). + feats (Tensor): + Feature tensor (B, aux_channels, T_feats,). + feats_lengths (Tensor): + Feature length tensor (B,). + sids (Optional[Tensor]): + Speaker index tensor (B,) or (B, 1). + spembs (Optional[Tensor]): + Speaker embedding tensor (B, spk_embed_dim). + lids (Optional[Tensor]): + Language index tensor (B,) or (B, 1). + dur (Optional[Tensor]): + Ground-truth duration (B, T_text,). If provided, skip the prediction of durations (i.e., teacher forcing). - noise_scale (float): Noise scale parameter for flow. - noise_scale_dur (float): Noise scale parameter for duration predictor. - alpha (float): Alpha parameter to control the speed of generated speech. - max_len (Optional[int]): Maximum length of acoustic feature sequence. - use_teacher_forcing (bool): Whether to use teacher forcing. + noise_scale (float): + Noise scale parameter for flow. + noise_scale_dur (float): + Noise scale parameter for duration predictor. + alpha (float): + Alpha parameter to control the speed of generated speech. + max_len (Optional[int]): + Maximum length of acoustic feature sequence. + use_teacher_forcing (bool): + Whether to use teacher forcing. Returns: - Tensor: Generated waveform tensor (B, T_wav). - Tensor: Monotonic attention weight tensor (B, T_feats, T_text). - Tensor: Duration tensor (B, T_text). + Tensor: + Generated waveform tensor (B, T_wav). + Tensor: + Monotonic attention weight tensor (B, T_feats, T_text). + Tensor: + Duration tensor (B, T_text). """ # encoder x, m_p, logs_p, x_mask = self.text_encoder(text, text_lengths) @@ -533,15 +585,23 @@ def voice_conversion( lids: Optional[paddle.Tensor]=None, ) -> paddle.Tensor: """Run voice conversion. Args: - feats (Tensor): Feature tensor (B, aux_channels, T_feats,). - feats_lengths (Tensor): Feature length tensor (B,). - sids_src (Optional[Tensor]): Speaker index tensor of source feature (B,) or (B, 1). - sids_tgt (Optional[Tensor]): Speaker index tensor of target feature (B,) or (B, 1). - spembs_src (Optional[Tensor]): Speaker embedding tensor of source feature (B, spk_embed_dim). - spembs_tgt (Optional[Tensor]): Speaker embedding tensor of target feature (B, spk_embed_dim). - lids (Optional[Tensor]): Language index tensor (B,) or (B, 1). + feats (Tensor): + Feature tensor (B, aux_channels, T_feats,). + feats_lengths (Tensor): + Feature length tensor (B,). + sids_src (Optional[Tensor]): + Speaker index tensor of source feature (B,) or (B, 1). + sids_tgt (Optional[Tensor]): + Speaker index tensor of target feature (B,) or (B, 1). + spembs_src (Optional[Tensor]): + Speaker embedding tensor of source feature (B, spk_embed_dim). + spembs_tgt (Optional[Tensor]): + Speaker embedding tensor of target feature (B, spk_embed_dim). + lids (Optional[Tensor]): + Language index tensor (B,) or (B, 1). Returns: - Tensor: Generated waveform tensor (B, T_wav). + Tensor: + Generated waveform tensor (B, T_wav). """ # encoder g_src = None @@ -602,10 +662,13 @@ def _generate_path(self, dur: paddle.Tensor, mask: paddle.Tensor) -> paddle.Tensor: """Generate path a.k.a. monotonic attention. Args: - dur (Tensor): Duration tensor (B, 1, T_text). - mask (Tensor): Attention mask tensor (B, 1, T_feats, T_text). + dur (Tensor): + Duration tensor (B, 1, T_text). + mask (Tensor): + Attention mask tensor (B, 1, T_feats, T_text). Returns: - Tensor: Path tensor (B, 1, T_feats, T_text). + Tensor: + Path tensor (B, 1, T_feats, T_text). """ b, _, t_y, t_x = paddle.shape(mask) cum_dur = paddle.cumsum(dur, -1) diff --git a/paddlespeech/t2s/models/vits/posterior_encoder.py b/paddlespeech/t2s/models/vits/posterior_encoder.py index 8532375576d..5e3d6b9ce34 100644 --- a/paddlespeech/t2s/models/vits/posterior_encoder.py +++ b/paddlespeech/t2s/models/vits/posterior_encoder.py @@ -52,17 +52,28 @@ def __init__( """Initilialize PosteriorEncoder module. Args: - in_channels (int): Number of input channels. - out_channels (int): Number of output channels. - hidden_channels (int): Number of hidden channels. - kernel_size (int): Kernel size in WaveNet. - layers (int): Number of layers of WaveNet. - stacks (int): Number of repeat stacking of WaveNet. - base_dilation (int): Base dilation factor. - global_channels (int): Number of global conditioning channels. - dropout_rate (float): Dropout rate. - bias (bool): Whether to use bias parameters in conv. - use_weight_norm (bool): Whether to apply weight norm. + in_channels (int): + Number of input channels. + out_channels (int): + Number of output channels. + hidden_channels (int): + Number of hidden channels. + kernel_size (int): + Kernel size in WaveNet. + layers (int): + Number of layers of WaveNet. + stacks (int): + Number of repeat stacking of WaveNet. + base_dilation (int): + Base dilation factor. + global_channels (int): + Number of global conditioning channels. + dropout_rate (float): + Dropout rate. + bias (bool): + Whether to use bias parameters in conv. + use_weight_norm (bool): + Whether to apply weight norm. """ super().__init__() @@ -99,15 +110,22 @@ def forward( """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, in_channels, T_feats). - x_lengths (Tensor): Length tensor (B,). - g (Optional[Tensor]): Global conditioning tensor (B, global_channels, 1). + x (Tensor): + Input tensor (B, in_channels, T_feats). + x_lengths (Tensor): + Length tensor (B,). + g (Optional[Tensor]): + Global conditioning tensor (B, global_channels, 1). Returns: - Tensor: Encoded hidden representation tensor (B, out_channels, T_feats). - Tensor: Projected mean tensor (B, out_channels, T_feats). - Tensor: Projected scale tensor (B, out_channels, T_feats). - Tensor: Mask tensor for input tensor (B, 1, T_feats). + Tensor: + Encoded hidden representation tensor (B, out_channels, T_feats). + Tensor: + Projected mean tensor (B, out_channels, T_feats). + Tensor: + Projected scale tensor (B, out_channels, T_feats). + Tensor: + Mask tensor for input tensor (B, 1, T_feats). """ x_mask = make_non_pad_mask(x_lengths).unsqueeze(1) diff --git a/paddlespeech/t2s/models/vits/residual_coupling.py b/paddlespeech/t2s/models/vits/residual_coupling.py index c18beedd038..afa6d1fa73b 100644 --- a/paddlespeech/t2s/models/vits/residual_coupling.py +++ b/paddlespeech/t2s/models/vits/residual_coupling.py @@ -55,18 +55,30 @@ def __init__( """Initilize ResidualAffineCouplingBlock module. Args: - in_channels (int): Number of input channels. - hidden_channels (int): Number of hidden channels. - flows (int): Number of flows. - kernel_size (int): Kernel size for WaveNet. - base_dilation (int): Base dilation factor for WaveNet. - layers (int): Number of layers of WaveNet. - stacks (int): Number of stacks of WaveNet. - global_channels (int): Number of global channels. - dropout_rate (float): Dropout rate. - use_weight_norm (bool): Whether to use weight normalization in WaveNet. - bias (bool): Whether to use bias paramters in WaveNet. - use_only_mean (bool): Whether to estimate only mean. + in_channels (int): + Number of input channels. + hidden_channels (int): + Number of hidden channels. + flows (int): + Number of flows. + kernel_size (int): + Kernel size for WaveNet. + base_dilation (int): + Base dilation factor for WaveNet. + layers (int): + Number of layers of WaveNet. + stacks (int): + Number of stacks of WaveNet. + global_channels (int): + Number of global channels. + dropout_rate (float): + Dropout rate. + use_weight_norm (bool): + Whether to use weight normalization in WaveNet. + bias (bool): + Whether to use bias paramters in WaveNet. + use_only_mean (bool): + Whether to estimate only mean. """ super().__init__() @@ -97,10 +109,14 @@ def forward( """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, in_channels, T). - x_mask (Tensor): Length tensor (B, 1, T). - g (Optional[Tensor]): Global conditioning tensor (B, global_channels, 1). - inverse (bool): Whether to inverse the flow. + x (Tensor): + Input tensor (B, in_channels, T). + x_mask (Tensor): + Length tensor (B, 1, T). + g (Optional[Tensor]): + Global conditioning tensor (B, global_channels, 1). + inverse (bool): + Whether to inverse the flow. Returns: Tensor: Output tensor (B, in_channels, T). @@ -134,17 +150,28 @@ def __init__( """Initialzie ResidualAffineCouplingLayer module. Args: - in_channels (int): Number of input channels. - hidden_channels (int): Number of hidden channels. - kernel_size (int): Kernel size for WaveNet. - base_dilation (int): Base dilation factor for WaveNet. - layers (int): Number of layers of WaveNet. - stacks (int): Number of stacks of WaveNet. - global_channels (int): Number of global channels. - dropout_rate (float): Dropout rate. - use_weight_norm (bool): Whether to use weight normalization in WaveNet. - bias (bool): Whether to use bias paramters in WaveNet. - use_only_mean (bool): Whether to estimate only mean. + in_channels (int): + Number of input channels. + hidden_channels (int): + Number of hidden channels. + kernel_size (int): + Kernel size for WaveNet. + base_dilation (int): + Base dilation factor for WaveNet. + layers (int): + Number of layers of WaveNet. + stacks (int): + Number of stacks of WaveNet. + global_channels (int): + Number of global channels. + dropout_rate (float): + Dropout rate. + use_weight_norm (bool): + Whether to use weight normalization in WaveNet. + bias (bool): + Whether to use bias paramters in WaveNet. + use_only_mean (bool): + Whether to estimate only mean. """ assert in_channels % 2 == 0, "in_channels should be divisible by 2" @@ -211,14 +238,20 @@ def forward( """Calculate forward propagation. Args: - x (Tensor): Input tensor (B, in_channels, T). - x_lengths (Tensor): Length tensor (B,). - g (Optional[Tensor]): Global conditioning tensor (B, global_channels, 1). - inverse (bool): Whether to inverse the flow. + x (Tensor): + Input tensor (B, in_channels, T). + x_lengths (Tensor): + Length tensor (B,). + g (Optional[Tensor]): + Global conditioning tensor (B, global_channels, 1). + inverse (bool): + Whether to inverse the flow. Returns: - Tensor: Output tensor (B, in_channels, T). - Tensor: Log-determinant tensor for NLL (B,) if not inverse. + Tensor: + Output tensor (B, in_channels, T). + Tensor: + Log-determinant tensor for NLL (B,) if not inverse. """ xa, xb = paddle.split(x, 2, axis=1) diff --git a/paddlespeech/t2s/models/vits/text_encoder.py b/paddlespeech/t2s/models/vits/text_encoder.py index 3afc7831ad1..799e0c75964 100644 --- a/paddlespeech/t2s/models/vits/text_encoder.py +++ b/paddlespeech/t2s/models/vits/text_encoder.py @@ -62,23 +62,40 @@ def __init__( """Initialize TextEncoder module. Args: - vocabs (int): Vocabulary size. - attention_dim (int): Attention dimension. - attention_heads (int): Number of attention heads. - linear_units (int): Number of linear units of positionwise layers. - blocks (int): Number of encoder blocks. - positionwise_layer_type (str): Positionwise layer type. - positionwise_conv_kernel_size (int): Positionwise layer's kernel size. - positional_encoding_layer_type (str): Positional encoding layer type. - self_attention_layer_type (str): Self-attention layer type. - activation_type (str): Activation function type. - normalize_before (bool): Whether to apply LayerNorm before attention. - use_macaron_style (bool): Whether to use macaron style components. - use_conformer_conv (bool): Whether to use conformer conv layers. - conformer_kernel_size (int): Conformer's conv kernel size. - dropout_rate (float): Dropout rate. - positional_dropout_rate (float): Dropout rate for positional encoding. - attention_dropout_rate (float): Dropout rate for attention. + vocabs (int): + Vocabulary size. + attention_dim (int): + Attention dimension. + attention_heads (int): + Number of attention heads. + linear_units (int): + Number of linear units of positionwise layers. + blocks (int): + Number of encoder blocks. + positionwise_layer_type (str): + Positionwise layer type. + positionwise_conv_kernel_size (int): + Positionwise layer's kernel size. + positional_encoding_layer_type (str): + Positional encoding layer type. + self_attention_layer_type (str): + Self-attention layer type. + activation_type (str): + Activation function type. + normalize_before (bool): + Whether to apply LayerNorm before attention. + use_macaron_style (bool): + Whether to use macaron style components. + use_conformer_conv (bool): + Whether to use conformer conv layers. + conformer_kernel_size (int): + Conformer's conv kernel size. + dropout_rate (float): + Dropout rate. + positional_dropout_rate (float): + Dropout rate for positional encoding. + attention_dropout_rate (float): + Dropout rate for attention. """ super().__init__() @@ -121,14 +138,20 @@ def forward( """Calculate forward propagation. Args: - x (Tensor): Input index tensor (B, T_text). - x_lengths (Tensor): Length tensor (B,). + x (Tensor): + Input index tensor (B, T_text). + x_lengths (Tensor): + Length tensor (B,). Returns: - Tensor: Encoded hidden representation (B, attention_dim, T_text). - Tensor: Projected mean tensor (B, attention_dim, T_text). - Tensor: Projected scale tensor (B, attention_dim, T_text). - Tensor: Mask tensor for input tensor (B, 1, T_text). + Tensor: + Encoded hidden representation (B, attention_dim, T_text). + Tensor: + Projected mean tensor (B, attention_dim, T_text). + Tensor: + Projected scale tensor (B, attention_dim, T_text). + Tensor: + Mask tensor for input tensor (B, 1, T_text). """ x = self.emb(x) * math.sqrt(self.attention_dim) diff --git a/paddlespeech/t2s/models/vits/vits.py b/paddlespeech/t2s/models/vits/vits.py index 983bf0a36f6..0ff3a546d0e 100644 --- a/paddlespeech/t2s/models/vits/vits.py +++ b/paddlespeech/t2s/models/vits/vits.py @@ -156,17 +156,25 @@ def __init__( init_type: str="xavier_uniform", ): """Initialize VITS module. Args: - idim (int): Input vocabrary size. - odim (int): Acoustic feature dimension. The actual output channels will + idim (int): + Input vocabrary size. + odim (int): + Acoustic feature dimension. The actual output channels will be 1 since VITS is the end-to-end text-to-wave model but for the compatibility odim is used to indicate the acoustic feature dimension. - sampling_rate (int): Sampling rate, not used for the training but it will + sampling_rate (int): + Sampling rate, not used for the training but it will be referred in saving waveform during the inference. - generator_type (str): Generator type. - generator_params (Dict[str, Any]): Parameter dict for generator. - discriminator_type (str): Discriminator type. - discriminator_params (Dict[str, Any]): Parameter dict for discriminator. - cache_generator_outputs (bool): Whether to cache generator outputs. + generator_type (str): + Generator type. + generator_params (Dict[str, Any]): + Parameter dict for generator. + discriminator_type (str): + Discriminator type. + discriminator_params (Dict[str, Any]): + Parameter dict for discriminator. + cache_generator_outputs (bool): + Whether to cache generator outputs. """ assert check_argument_types() super().__init__() @@ -218,14 +226,22 @@ def forward( forward_generator: bool=True, ) -> Dict[str, Any]: """Perform generator forward. Args: - text (Tensor): Text index tensor (B, T_text). - text_lengths (Tensor): Text length tensor (B,). - feats (Tensor): Feature tensor (B, T_feats, aux_channels). - feats_lengths (Tensor): Feature length tensor (B,). - sids (Optional[Tensor]): Speaker index tensor (B,) or (B, 1). - spembs (Optional[Tensor]): Speaker embedding tensor (B, spk_embed_dim). - lids (Optional[Tensor]): Language index tensor (B,) or (B, 1). - forward_generator (bool): Whether to forward generator. + text (Tensor): + Text index tensor (B, T_text). + text_lengths (Tensor): + Text length tensor (B,). + feats (Tensor): + Feature tensor (B, T_feats, aux_channels). + feats_lengths (Tensor): + Feature length tensor (B,). + sids (Optional[Tensor]): + Speaker index tensor (B,) or (B, 1). + spembs (Optional[Tensor]): + Speaker embedding tensor (B, spk_embed_dim). + lids (Optional[Tensor]): + Language index tensor (B,) or (B, 1). + forward_generator (bool): + Whether to forward generator. Returns: """ @@ -259,13 +275,20 @@ def _forward_generator( lids: Optional[paddle.Tensor]=None, ) -> Dict[str, Any]: """Perform generator forward. Args: - text (Tensor): Text index tensor (B, T_text). - text_lengths (Tensor): Text length tensor (B,). - feats (Tensor): Feature tensor (B, T_feats, aux_channels). - feats_lengths (Tensor): Feature length tensor (B,). - sids (Optional[Tensor]): Speaker index tensor (B,) or (B, 1). - spembs (Optional[Tensor]): Speaker embedding tensor (B, spk_embed_dim). - lids (Optional[Tensor]): Language index tensor (B,) or (B, 1). + text (Tensor): + Text index tensor (B, T_text). + text_lengths (Tensor): + Text length tensor (B,). + feats (Tensor): + Feature tensor (B, T_feats, aux_channels). + feats_lengths (Tensor): + Feature length tensor (B,). + sids (Optional[Tensor]): + Speaker index tensor (B,) or (B, 1). + spembs (Optional[Tensor]): + Speaker embedding tensor (B, spk_embed_dim). + lids (Optional[Tensor]): + Language index tensor (B,) or (B, 1). Returns: """ @@ -304,13 +327,20 @@ def _forward_discrminator( lids: Optional[paddle.Tensor]=None, ) -> Dict[str, Any]: """Perform discriminator forward. Args: - text (Tensor): Text index tensor (B, T_text). - text_lengths (Tensor): Text length tensor (B,). - feats (Tensor): Feature tensor (B, T_feats, aux_channels). - feats_lengths (Tensor): Feature length tensor (B,). - sids (Optional[Tensor]): Speaker index tensor (B,) or (B, 1). - spembs (Optional[Tensor]): Speaker embedding tensor (B, spk_embed_dim). - lids (Optional[Tensor]): Language index tensor (B,) or (B, 1). + text (Tensor): + Text index tensor (B, T_text). + text_lengths (Tensor): + Text length tensor (B,). + feats (Tensor): + Feature tensor (B, T_feats, aux_channels). + feats_lengths (Tensor): + Feature length tensor (B,). + sids (Optional[Tensor]): + Speaker index tensor (B,) or (B, 1). + spembs (Optional[Tensor]): + Speaker embedding tensor (B, spk_embed_dim). + lids (Optional[Tensor]): + Language index tensor (B,) or (B, 1). Returns: """ @@ -353,22 +383,36 @@ def inference( use_teacher_forcing: bool=False, ) -> Dict[str, paddle.Tensor]: """Run inference. Args: - text (Tensor): Input text index tensor (T_text,). - feats (Tensor): Feature tensor (T_feats, aux_channels). - sids (Tensor): Speaker index tensor (1,). - spembs (Optional[Tensor]): Speaker embedding tensor (spk_embed_dim,). - lids (Tensor): Language index tensor (1,). - durations (Tensor): Ground-truth duration tensor (T_text,). - noise_scale (float): Noise scale value for flow. - noise_scale_dur (float): Noise scale value for duration predictor. - alpha (float): Alpha parameter to control the speed of generated speech. - max_len (Optional[int]): Maximum length. - use_teacher_forcing (bool): Whether to use teacher forcing. + text (Tensor): + Input text index tensor (T_text,). + feats (Tensor): + Feature tensor (T_feats, aux_channels). + sids (Tensor): + Speaker index tensor (1,). + spembs (Optional[Tensor]): + Speaker embedding tensor (spk_embed_dim,). + lids (Tensor): + Language index tensor (1,). + durations (Tensor): + Ground-truth duration tensor (T_text,). + noise_scale (float): + Noise scale value for flow. + noise_scale_dur (float): + Noise scale value for duration predictor. + alpha (float): + Alpha parameter to control the speed of generated speech. + max_len (Optional[int]): + Maximum length. + use_teacher_forcing (bool): + Whether to use teacher forcing. Returns: Dict[str, Tensor]: - * wav (Tensor): Generated waveform tensor (T_wav,). - * att_w (Tensor): Monotonic attention weight tensor (T_feats, T_text). - * duration (Tensor): Predicted duration tensor (T_text,). + * wav (Tensor): + Generated waveform tensor (T_wav,). + * att_w (Tensor): + Monotonic attention weight tensor (T_feats, T_text). + * duration (Tensor): + Predicted duration tensor (T_text,). """ # setup text = text[None] @@ -417,15 +461,22 @@ def voice_conversion( lids: Optional[paddle.Tensor]=None, ) -> paddle.Tensor: """Run voice conversion. Args: - feats (Tensor): Feature tensor (T_feats, aux_channels). - sids_src (Optional[Tensor]): Speaker index tensor of source feature (1,). - sids_tgt (Optional[Tensor]): Speaker index tensor of target feature (1,). - spembs_src (Optional[Tensor]): Speaker embedding tensor of source feature (spk_embed_dim,). - spembs_tgt (Optional[Tensor]): Speaker embedding tensor of target feature (spk_embed_dim,). - lids (Optional[Tensor]): Language index tensor (1,). + feats (Tensor): + Feature tensor (T_feats, aux_channels). + sids_src (Optional[Tensor]): + Speaker index tensor of source feature (1,). + sids_tgt (Optional[Tensor]): + Speaker index tensor of target feature (1,). + spembs_src (Optional[Tensor]): + Speaker embedding tensor of source feature (spk_embed_dim,). + spembs_tgt (Optional[Tensor]): + Speaker embedding tensor of target feature (spk_embed_dim,). + lids (Optional[Tensor]): + Language index tensor (1,). Returns: Dict[str, Tensor]: - * wav (Tensor): Generated waveform tensor (T_wav,). + * wav (Tensor): + Generated waveform tensor (T_wav,). """ assert feats is not None feats = feats[None].transpose([0, 2, 1]) diff --git a/paddlespeech/t2s/models/vits/wavenet/residual_block.py b/paddlespeech/t2s/models/vits/wavenet/residual_block.py index 197e7497557..b5095e16872 100644 --- a/paddlespeech/t2s/models/vits/wavenet/residual_block.py +++ b/paddlespeech/t2s/models/vits/wavenet/residual_block.py @@ -39,14 +39,22 @@ def __init__( """Initialize ResidualBlock module. Args: - kernel_size (int): Kernel size of dilation convolution layer. - residual_channels (int): Number of channels for residual connection. - skip_channels (int): Number of channels for skip connection. - aux_channels (int): Number of local conditioning channels. - dropout (float): Dropout probability. - dilation (int): Dilation factor. - bias (bool): Whether to add bias parameter in convolution layers. - scale_residual (bool): Whether to scale the residual outputs. + kernel_size (int): + Kernel size of dilation convolution layer. + residual_channels (int): + Number of channels for residual connection. + skip_channels (int): + Number of channels for skip connection. + aux_channels (int): + Number of local conditioning channels. + dropout (float): + Dropout probability. + dilation (int): + Dilation factor. + bias (bool): + Whether to add bias parameter in convolution layers. + scale_residual (bool): + Whether to scale the residual outputs. """ super().__init__() diff --git a/paddlespeech/t2s/models/vits/wavenet/wavenet.py b/paddlespeech/t2s/models/vits/wavenet/wavenet.py index 44693dac614..04422939bc5 100644 --- a/paddlespeech/t2s/models/vits/wavenet/wavenet.py +++ b/paddlespeech/t2s/models/vits/wavenet/wavenet.py @@ -47,25 +47,42 @@ def __init__( """Initialize WaveNet module. Args: - in_channels (int): Number of input channels. - out_channels (int): Number of output channels. - kernel_size (int): Kernel size of dilated convolution. - layers (int): Number of residual block layers. - stacks (int): Number of stacks i.e., dilation cycles. - base_dilation (int): Base dilation factor. - residual_channels (int): Number of channels in residual conv. - gate_channels (int): Number of channels in gated conv. - skip_channels (int): Number of channels in skip conv. - aux_channels (int): Number of channels for local conditioning feature. - global_channels (int): Number of channels for global conditioning feature. - dropout_rate (float): Dropout rate. 0.0 means no dropout applied. - bias (bool): Whether to use bias parameter in conv layer. - use_weight_norm (bool): Whether to use weight norm. If set to true, it will - be applied to all of the conv layers. - use_first_conv (bool): Whether to use the first conv layers. - use_last_conv (bool): Whether to use the last conv layers. - scale_residual (bool): Whether to scale the residual outputs. - scale_skip_connect (bool): Whether to scale the skip connection outputs. + in_channels (int): + Number of input channels. + out_channels (int): + Number of output channels. + kernel_size (int): + Kernel size of dilated convolution. + layers (int): + Number of residual block layers. + stacks (int): + Number of stacks i.e., dilation cycles. + base_dilation (int): + Base dilation factor. + residual_channels (int): + Number of channels in residual conv. + gate_channels (int): + Number of channels in gated conv. + skip_channels (int): + Number of channels in skip conv. + aux_channels (int): + Number of channels for local conditioning feature. + global_channels (int): + Number of channels for global conditioning feature. + dropout_rate (float): + Dropout rate. 0.0 means no dropout applied. + bias (bool): + Whether to use bias parameter in conv layer. + use_weight_norm (bool): + Whether to use weight norm. If set to true, it will be applied to all of the conv layers. + use_first_conv (bool): + Whether to use the first conv layers. + use_last_conv (bool): + Whether to use the last conv layers. + scale_residual (bool): + Whether to scale the residual outputs. + scale_skip_connect (bool): + Whether to scale the skip connection outputs. """ super().__init__() @@ -128,15 +145,18 @@ def forward( """Calculate forward propagation. Args: - x (Tensor): Input noise signal (B, 1, T) if use_first_conv else - (B, residual_channels, T). - x_mask (Optional[Tensor]): Mask tensor (B, 1, T). - c (Optional[Tensor]): Local conditioning features (B, aux_channels, T). - g (Optional[Tensor]): Global conditioning features (B, global_channels, 1). + x (Tensor): + Input noise signal (B, 1, T) if use_first_conv else (B, residual_channels, T). + x_mask (Optional[Tensor]): + Mask tensor (B, 1, T). + c (Optional[Tensor]): + Local conditioning features (B, aux_channels, T). + g (Optional[Tensor]): + Global conditioning features (B, global_channels, 1). Returns: - Tensor: Output tensor (B, out_channels, T) if use_last_conv else - (B, residual_channels, T). + Tensor: + Output tensor (B, out_channels, T) if use_last_conv else(B, residual_channels, T). """ # encode to hidden representation diff --git a/paddlespeech/t2s/models/wavernn/wavernn.py b/paddlespeech/t2s/models/wavernn/wavernn.py index 254edbb2df0..44e9f2d8df8 100644 --- a/paddlespeech/t2s/models/wavernn/wavernn.py +++ b/paddlespeech/t2s/models/wavernn/wavernn.py @@ -69,9 +69,11 @@ def __init__(self, def forward(self, x): ''' Args: - x (Tensor): Input tensor (B, in_dims, T). + x (Tensor): + Input tensor (B, in_dims, T). Returns: - Tensor: Output tensor (B, res_out_dims, T). + Tensor: + Output tensor (B, res_out_dims, T). ''' x = self.conv_in(x) @@ -119,10 +121,13 @@ def __init__(self, def forward(self, m): ''' Args: - c (Tensor): Input tensor (B, C_aux, T). + c (Tensor): + Input tensor (B, C_aux, T). Returns: - Tensor: Output tensor (B, (T - 2 * pad) * prob(upsample_scales), C_aux). - Tensor: Output tensor (B, (T - 2 * pad) * prob(upsample_scales), res_out_dims). + Tensor: + Output tensor (B, (T - 2 * pad) * prob(upsample_scales), C_aux). + Tensor: + Output tensor (B, (T - 2 * pad) * prob(upsample_scales), res_out_dims). ''' # aux: [B, C_aux, T] # -> [B, res_out_dims, T - 2 * aux_context_window] @@ -302,7 +307,8 @@ def generate(self, number of samples for crossfading between batches mu_law(bool) Returns: - wav sequence: Output (T' * prod(upsample_scales), out_channels, C_out). + wav sequence: + Output (T' * prod(upsample_scales), out_channels, C_out). """ self.eval() @@ -423,7 +429,7 @@ def pad_tensor(self, x, pad, side='both'): x(Tensor): mel, [1, n_frames, 80] pad(int): - side(str, optional): (Default value = 'both') + side(str, optional): (Default value = 'both') Returns: Tensor