huggingface · sgugger · Apr 4, 2022 · Mar 31, 2022 · Mar 31, 2022 · Mar 31, 2022
diff --git a/.github/workflows/build_documentation.yml b/.github/workflows/build_documentation.yml
@@ -15,5 +15,6 @@ jobs:
       commit_sha: ${{ github.sha }}
       package: transformers
       notebook_folder: transformers_doc
+      languages: en es
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}
diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml
@@ -14,3 +14,4 @@ jobs:
       commit_sha: ${{ github.event.pull_request.head.sha }}
       pr_number: ${{ github.event.number }}
       package: transformers
+      languages: en es
diff --git a/docs/source/contributing.md b/docs/source/contributing.md
diff --git a/docs/source/en/_config.py b/docs/source/en/_config.py
@@ -0,0 +1,14 @@
+# docstyle-ignore
+INSTALL_CONTENT = """
+# Transformers installation
+! pip install transformers datasets
+# To install from source instead of the last release, comment the command above and uncomment the following one.
+# ! pip install git+https://github.com/huggingface/transformers.git
+"""
+
+notebook_first_cells = [{"type": "code", "content": INSTALL_CONTENT}]
+black_avoid_patterns = {
+    "{processor_class}": "FakeProcessorClass",
+    "{model_class}": "FakeModelClass",
+    "{object_class}": "FakeObjectClass",    
+}
diff --git a/docs/source/_toctree.yml → docs/source/en/_toctree.yml b/docs/source/_toctree.yml → docs/source/en/_toctree.yml
diff --git a/docs/source/accelerate.mdx → docs/source/en/accelerate.mdx b/docs/source/accelerate.mdx → docs/source/en/accelerate.mdx
diff --git a/docs/source/add_new_model.mdx → docs/source/en/add_new_model.mdx b/docs/source/add_new_model.mdx → docs/source/en/add_new_model.mdx
diff --git a/docs/source/add_new_pipeline.mdx → docs/source/en/add_new_pipeline.mdx b/docs/source/add_new_pipeline.mdx → docs/source/en/add_new_pipeline.mdx
diff --git a/docs/source/autoclass_tutorial.mdx → docs/source/en/autoclass_tutorial.mdx b/docs/source/autoclass_tutorial.mdx → docs/source/en/autoclass_tutorial.mdx
diff --git a/docs/source/benchmarks.mdx → docs/source/en/benchmarks.mdx b/docs/source/benchmarks.mdx → docs/source/en/benchmarks.mdx
diff --git a/docs/source/bertology.mdx → docs/source/en/bertology.mdx b/docs/source/bertology.mdx → docs/source/en/bertology.mdx
diff --git a/docs/source/community.mdx → docs/source/en/community.mdx b/docs/source/community.mdx → docs/source/en/community.mdx
diff --git a/docs/source/en/contributing.md b/docs/source/en/contributing.md
@@ -0,0 +1 @@
+../../../CONTRIBUTING.md
diff --git a/docs/source/converting_tensorflow_models.mdx → ...ource/en/converting_tensorflow_models.mdx b/docs/source/converting_tensorflow_models.mdx → ...ource/en/converting_tensorflow_models.mdx
diff --git a/docs/source/create_a_model.mdx → docs/source/en/create_a_model.mdx b/docs/source/create_a_model.mdx → docs/source/en/create_a_model.mdx
diff --git a/docs/source/custom_models.mdx → docs/source/en/custom_models.mdx b/docs/source/custom_models.mdx → docs/source/en/custom_models.mdx
diff --git a/docs/source/debugging.mdx → docs/source/en/debugging.mdx b/docs/source/debugging.mdx → docs/source/en/debugging.mdx
diff --git a/docs/source/fast_tokenizers.mdx → docs/source/en/fast_tokenizers.mdx b/docs/source/fast_tokenizers.mdx → docs/source/en/fast_tokenizers.mdx
diff --git a/docs/source/glossary.mdx → docs/source/en/glossary.mdx b/docs/source/glossary.mdx → docs/source/en/glossary.mdx
diff --git a/docs/source/index.mdx → docs/source/en/index.mdx b/docs/source/index.mdx → docs/source/en/index.mdx
diff --git a/docs/source/installation.mdx → docs/source/en/installation.mdx b/docs/source/installation.mdx → docs/source/en/installation.mdx
diff --git a/docs/source/internal/file_utils.mdx → docs/source/en/internal/file_utils.mdx b/docs/source/internal/file_utils.mdx → docs/source/en/internal/file_utils.mdx
diff --git a/docs/source/internal/generation_utils.mdx → docs/source/en/internal/generation_utils.mdx b/docs/source/internal/generation_utils.mdx → docs/source/en/internal/generation_utils.mdx
diff --git a/docs/source/internal/modeling_utils.mdx → docs/source/en/internal/modeling_utils.mdx b/docs/source/internal/modeling_utils.mdx → docs/source/en/internal/modeling_utils.mdx
diff --git a/docs/source/internal/pipelines_utils.mdx → docs/source/en/internal/pipelines_utils.mdx b/docs/source/internal/pipelines_utils.mdx → docs/source/en/internal/pipelines_utils.mdx
diff --git a/docs/source/internal/tokenization_utils.mdx → ...source/en/internal/tokenization_utils.mdx b/docs/source/internal/tokenization_utils.mdx → ...source/en/internal/tokenization_utils.mdx
diff --git a/docs/source/internal/trainer_utils.mdx → docs/source/en/internal/trainer_utils.mdx b/docs/source/internal/trainer_utils.mdx → docs/source/en/internal/trainer_utils.mdx
diff --git a/docs/source/main_classes/callback.mdx → docs/source/en/main_classes/callback.mdx b/docs/source/main_classes/callback.mdx → docs/source/en/main_classes/callback.mdx
diff --git a/docs/source/main_classes/configuration.mdx → .../source/en/main_classes/configuration.mdx b/docs/source/main_classes/configuration.mdx → .../source/en/main_classes/configuration.mdx
diff --git a/docs/source/main_classes/data_collator.mdx → .../source/en/main_classes/data_collator.mdx b/docs/source/main_classes/data_collator.mdx → .../source/en/main_classes/data_collator.mdx
diff --git a/docs/source/main_classes/deepspeed.mdx → docs/source/en/main_classes/deepspeed.mdx b/docs/source/main_classes/deepspeed.mdx → docs/source/en/main_classes/deepspeed.mdx
diff --git a/...source/main_classes/feature_extractor.mdx → ...rce/en/main_classes/feature_extractor.mdx b/...source/main_classes/feature_extractor.mdx → ...rce/en/main_classes/feature_extractor.mdx
diff --git a/docs/source/main_classes/keras_callbacks.mdx → ...ource/en/main_classes/keras_callbacks.mdx b/docs/source/main_classes/keras_callbacks.mdx → ...ource/en/main_classes/keras_callbacks.mdx
diff --git a/docs/source/main_classes/logging.mdx → docs/source/en/main_classes/logging.mdx b/docs/source/main_classes/logging.mdx → docs/source/en/main_classes/logging.mdx
diff --git a/docs/source/main_classes/model.mdx → docs/source/en/main_classes/model.mdx b/docs/source/main_classes/model.mdx → docs/source/en/main_classes/model.mdx
diff --git a/docs/source/main_classes/onnx.mdx → docs/source/en/main_classes/onnx.mdx b/docs/source/main_classes/onnx.mdx → docs/source/en/main_classes/onnx.mdx
diff --git a/...urce/main_classes/optimizer_schedules.mdx → ...e/en/main_classes/optimizer_schedules.mdx b/...urce/main_classes/optimizer_schedules.mdx → ...e/en/main_classes/optimizer_schedules.mdx
diff --git a/docs/source/main_classes/output.mdx → docs/source/en/main_classes/output.mdx b/docs/source/main_classes/output.mdx → docs/source/en/main_classes/output.mdx
diff --git a/docs/source/main_classes/pipelines.mdx → docs/source/en/main_classes/pipelines.mdx b/docs/source/main_classes/pipelines.mdx → docs/source/en/main_classes/pipelines.mdx
diff --git a/docs/source/main_classes/processors.mdx → docs/source/en/main_classes/processors.mdx b/docs/source/main_classes/processors.mdx → docs/source/en/main_classes/processors.mdx
diff --git a/docs/source/main_classes/text_generation.mdx → ...ource/en/main_classes/text_generation.mdx b/docs/source/main_classes/text_generation.mdx → ...ource/en/main_classes/text_generation.mdx
diff --git a/docs/source/main_classes/tokenizer.mdx → docs/source/en/main_classes/tokenizer.mdx b/docs/source/main_classes/tokenizer.mdx → docs/source/en/main_classes/tokenizer.mdx
diff --git a/docs/source/main_classes/trainer.mdx → docs/source/en/main_classes/trainer.mdx b/docs/source/main_classes/trainer.mdx → docs/source/en/main_classes/trainer.mdx
diff --git a/docs/source/migration.mdx → docs/source/en/migration.mdx b/docs/source/migration.mdx → docs/source/en/migration.mdx
diff --git a/docs/source/model_doc/albert.mdx → docs/source/en/model_doc/albert.mdx b/docs/source/model_doc/albert.mdx → docs/source/en/model_doc/albert.mdx
diff --git a/docs/source/model_doc/auto.mdx → docs/source/en/model_doc/auto.mdx b/docs/source/model_doc/auto.mdx → docs/source/en/model_doc/auto.mdx
diff --git a/docs/source/model_doc/bart.mdx → docs/source/en/model_doc/bart.mdx b/docs/source/model_doc/bart.mdx → docs/source/en/model_doc/bart.mdx
diff --git a/docs/source/model_doc/barthez.mdx → docs/source/en/model_doc/barthez.mdx b/docs/source/model_doc/barthez.mdx → docs/source/en/model_doc/barthez.mdx
diff --git a/docs/source/model_doc/bartpho.mdx → docs/source/en/model_doc/bartpho.mdx b/docs/source/model_doc/bartpho.mdx → docs/source/en/model_doc/bartpho.mdx
diff --git a/docs/source/model_doc/beit.mdx → docs/source/en/model_doc/beit.mdx b/docs/source/model_doc/beit.mdx → docs/source/en/model_doc/beit.mdx
diff --git a/docs/source/model_doc/bert-generation.mdx → docs/source/en/model_doc/bert-generation.mdx b/docs/source/model_doc/bert-generation.mdx → docs/source/en/model_doc/bert-generation.mdx
diff --git a/docs/source/model_doc/bert-japanese.mdx → docs/source/en/model_doc/bert-japanese.mdx b/docs/source/model_doc/bert-japanese.mdx → docs/source/en/model_doc/bert-japanese.mdx
diff --git a/docs/source/model_doc/bert.mdx → docs/source/en/model_doc/bert.mdx b/docs/source/model_doc/bert.mdx → docs/source/en/model_doc/bert.mdx
diff --git a/docs/source/model_doc/bertweet.mdx → docs/source/en/model_doc/bertweet.mdx b/docs/source/model_doc/bertweet.mdx → docs/source/en/model_doc/bertweet.mdx
diff --git a/docs/source/model_doc/big_bird.mdx → docs/source/en/model_doc/big_bird.mdx b/docs/source/model_doc/big_bird.mdx → docs/source/en/model_doc/big_bird.mdx
diff --git a/docs/source/model_doc/bigbird_pegasus.mdx → docs/source/en/model_doc/bigbird_pegasus.mdx b/docs/source/model_doc/bigbird_pegasus.mdx → docs/source/en/model_doc/bigbird_pegasus.mdx
diff --git a/docs/source/model_doc/blenderbot-small.mdx → .../source/en/model_doc/blenderbot-small.mdx b/docs/source/model_doc/blenderbot-small.mdx → .../source/en/model_doc/blenderbot-small.mdx
diff --git a/docs/source/model_doc/blenderbot.mdx → docs/source/en/model_doc/blenderbot.mdx b/docs/source/model_doc/blenderbot.mdx → docs/source/en/model_doc/blenderbot.mdx
diff --git a/docs/source/model_doc/bort.mdx → docs/source/en/model_doc/bort.mdx b/docs/source/model_doc/bort.mdx → docs/source/en/model_doc/bort.mdx
diff --git a/docs/source/model_doc/byt5.mdx → docs/source/en/model_doc/byt5.mdx b/docs/source/model_doc/byt5.mdx → docs/source/en/model_doc/byt5.mdx
diff --git a/docs/source/model_doc/camembert.mdx → docs/source/en/model_doc/camembert.mdx b/docs/source/model_doc/camembert.mdx → docs/source/en/model_doc/camembert.mdx
diff --git a/docs/source/model_doc/canine.mdx → docs/source/en/model_doc/canine.mdx b/docs/source/model_doc/canine.mdx → docs/source/en/model_doc/canine.mdx
diff --git a/docs/source/model_doc/clip.mdx → docs/source/en/model_doc/clip.mdx b/docs/source/model_doc/clip.mdx → docs/source/en/model_doc/clip.mdx
diff --git a/docs/source/model_doc/convbert.mdx → docs/source/en/model_doc/convbert.mdx b/docs/source/model_doc/convbert.mdx → docs/source/en/model_doc/convbert.mdx
diff --git a/docs/source/model_doc/convnext.mdx → docs/source/en/model_doc/convnext.mdx b/docs/source/model_doc/convnext.mdx → docs/source/en/model_doc/convnext.mdx
diff --git a/docs/source/model_doc/cpm.mdx → docs/source/en/model_doc/cpm.mdx b/docs/source/model_doc/cpm.mdx → docs/source/en/model_doc/cpm.mdx
diff --git a/docs/source/model_doc/ctrl.mdx → docs/source/en/model_doc/ctrl.mdx b/docs/source/model_doc/ctrl.mdx → docs/source/en/model_doc/ctrl.mdx
diff --git a/docs/source/model_doc/data2vec.mdx → docs/source/en/model_doc/data2vec.mdx b/docs/source/model_doc/data2vec.mdx → docs/source/en/model_doc/data2vec.mdx
diff --git a/docs/source/model_doc/deberta-v2.mdx → docs/source/en/model_doc/deberta-v2.mdx b/docs/source/model_doc/deberta-v2.mdx → docs/source/en/model_doc/deberta-v2.mdx
diff --git a/docs/source/model_doc/deberta.mdx → docs/source/en/model_doc/deberta.mdx b/docs/source/model_doc/deberta.mdx → docs/source/en/model_doc/deberta.mdx
diff --git a/...source/model_doc/decision_transformer.mdx → ...rce/en/model_doc/decision_transformer.mdx b/...source/model_doc/decision_transformer.mdx → ...rce/en/model_doc/decision_transformer.mdx
diff --git a/docs/source/model_doc/deit.mdx → docs/source/en/model_doc/deit.mdx b/docs/source/model_doc/deit.mdx → docs/source/en/model_doc/deit.mdx
diff --git a/docs/source/model_doc/detr.mdx → docs/source/en/model_doc/detr.mdx b/docs/source/model_doc/detr.mdx → docs/source/en/model_doc/detr.mdx
diff --git a/docs/source/model_doc/dialogpt.mdx → docs/source/en/model_doc/dialogpt.mdx b/docs/source/model_doc/dialogpt.mdx → docs/source/en/model_doc/dialogpt.mdx
diff --git a/docs/source/model_doc/distilbert.mdx → docs/source/en/model_doc/distilbert.mdx b/docs/source/model_doc/distilbert.mdx → docs/source/en/model_doc/distilbert.mdx
diff --git a/docs/source/model_doc/dit.mdx → docs/source/en/model_doc/dit.mdx b/docs/source/model_doc/dit.mdx → docs/source/en/model_doc/dit.mdx
diff --git a/docs/source/model_doc/dpr.mdx → docs/source/en/model_doc/dpr.mdx b/docs/source/model_doc/dpr.mdx → docs/source/en/model_doc/dpr.mdx
diff --git a/docs/source/model_doc/dpt.mdx → docs/source/en/model_doc/dpt.mdx b/docs/source/model_doc/dpt.mdx → docs/source/en/model_doc/dpt.mdx
diff --git a/docs/source/model_doc/electra.mdx → docs/source/en/model_doc/electra.mdx b/docs/source/model_doc/electra.mdx → docs/source/en/model_doc/electra.mdx
diff --git a/docs/source/model_doc/encoder-decoder.mdx → docs/source/en/model_doc/encoder-decoder.mdx b/docs/source/model_doc/encoder-decoder.mdx → docs/source/en/model_doc/encoder-decoder.mdx
diff --git a/docs/source/model_doc/flaubert.mdx → docs/source/en/model_doc/flaubert.mdx b/docs/source/model_doc/flaubert.mdx → docs/source/en/model_doc/flaubert.mdx
diff --git a/docs/source/model_doc/fnet.mdx → docs/source/en/model_doc/fnet.mdx b/docs/source/model_doc/fnet.mdx → docs/source/en/model_doc/fnet.mdx
diff --git a/docs/source/model_doc/fsmt.mdx → docs/source/en/model_doc/fsmt.mdx b/docs/source/model_doc/fsmt.mdx → docs/source/en/model_doc/fsmt.mdx
diff --git a/docs/source/model_doc/funnel.mdx → docs/source/en/model_doc/funnel.mdx b/docs/source/model_doc/funnel.mdx → docs/source/en/model_doc/funnel.mdx
diff --git a/docs/source/model_doc/glpn.mdx → docs/source/en/model_doc/glpn.mdx b/docs/source/model_doc/glpn.mdx → docs/source/en/model_doc/glpn.mdx
diff --git a/docs/source/model_doc/gpt2.mdx → docs/source/en/model_doc/gpt2.mdx b/docs/source/model_doc/gpt2.mdx → docs/source/en/model_doc/gpt2.mdx
diff --git a/docs/source/model_doc/gpt_neo.mdx → docs/source/en/model_doc/gpt_neo.mdx b/docs/source/model_doc/gpt_neo.mdx → docs/source/en/model_doc/gpt_neo.mdx
diff --git a/docs/source/model_doc/gptj.mdx → docs/source/en/model_doc/gptj.mdx b/docs/source/model_doc/gptj.mdx → docs/source/en/model_doc/gptj.mdx
diff --git a/docs/source/model_doc/herbert.mdx → docs/source/en/model_doc/herbert.mdx b/docs/source/model_doc/herbert.mdx → docs/source/en/model_doc/herbert.mdx
diff --git a/docs/source/model_doc/hubert.mdx → docs/source/en/model_doc/hubert.mdx b/docs/source/model_doc/hubert.mdx → docs/source/en/model_doc/hubert.mdx
diff --git a/docs/source/model_doc/ibert.mdx → docs/source/en/model_doc/ibert.mdx b/docs/source/model_doc/ibert.mdx → docs/source/en/model_doc/ibert.mdx
diff --git a/docs/source/model_doc/imagegpt.mdx → docs/source/en/model_doc/imagegpt.mdx b/docs/source/model_doc/imagegpt.mdx → docs/source/en/model_doc/imagegpt.mdx
diff --git a/docs/source/model_doc/layoutlm.mdx → docs/source/en/model_doc/layoutlm.mdx b/docs/source/model_doc/layoutlm.mdx → docs/source/en/model_doc/layoutlm.mdx
diff --git a/docs/source/model_doc/layoutlmv2.mdx → docs/source/en/model_doc/layoutlmv2.mdx b/docs/source/model_doc/layoutlmv2.mdx → docs/source/en/model_doc/layoutlmv2.mdx
diff --git a/docs/source/model_doc/layoutxlm.mdx → docs/source/en/model_doc/layoutxlm.mdx b/docs/source/model_doc/layoutxlm.mdx → docs/source/en/model_doc/layoutxlm.mdx
diff --git a/docs/source/model_doc/led.mdx → docs/source/en/model_doc/led.mdx b/docs/source/model_doc/led.mdx → docs/source/en/model_doc/led.mdx
diff --git a/docs/source/model_doc/longformer.mdx → docs/source/en/model_doc/longformer.mdx b/docs/source/model_doc/longformer.mdx → docs/source/en/model_doc/longformer.mdx
diff --git a/docs/source/model_doc/luke.mdx → docs/source/en/model_doc/luke.mdx b/docs/source/model_doc/luke.mdx → docs/source/en/model_doc/luke.mdx
diff --git a/docs/source/model_doc/lxmert.mdx → docs/source/en/model_doc/lxmert.mdx b/docs/source/model_doc/lxmert.mdx → docs/source/en/model_doc/lxmert.mdx
diff --git a/docs/source/model_doc/m2m_100.mdx → docs/source/en/model_doc/m2m_100.mdx b/docs/source/model_doc/m2m_100.mdx → docs/source/en/model_doc/m2m_100.mdx
diff --git a/docs/source/model_doc/marian.mdx → docs/source/en/model_doc/marian.mdx b/docs/source/model_doc/marian.mdx → docs/source/en/model_doc/marian.mdx
diff --git a/docs/source/model_doc/maskformer.mdx → docs/source/en/model_doc/maskformer.mdx b/docs/source/model_doc/maskformer.mdx → docs/source/en/model_doc/maskformer.mdx
diff --git a/docs/source/model_doc/mbart.mdx → docs/source/en/model_doc/mbart.mdx b/docs/source/model_doc/mbart.mdx → docs/source/en/model_doc/mbart.mdx
diff --git a/docs/source/model_doc/megatron-bert.mdx → docs/source/en/model_doc/megatron-bert.mdx b/docs/source/model_doc/megatron-bert.mdx → docs/source/en/model_doc/megatron-bert.mdx
diff --git a/docs/source/model_doc/megatron_gpt2.mdx → docs/source/en/model_doc/megatron_gpt2.mdx b/docs/source/model_doc/megatron_gpt2.mdx → docs/source/en/model_doc/megatron_gpt2.mdx
diff --git a/docs/source/model_doc/mluke.mdx → docs/source/en/model_doc/mluke.mdx b/docs/source/model_doc/mluke.mdx → docs/source/en/model_doc/mluke.mdx
diff --git a/docs/source/model_doc/mobilebert.mdx → docs/source/en/model_doc/mobilebert.mdx b/docs/source/model_doc/mobilebert.mdx → docs/source/en/model_doc/mobilebert.mdx
diff --git a/docs/source/model_doc/mpnet.mdx → docs/source/en/model_doc/mpnet.mdx b/docs/source/model_doc/mpnet.mdx → docs/source/en/model_doc/mpnet.mdx
diff --git a/docs/source/model_doc/mt5.mdx → docs/source/en/model_doc/mt5.mdx b/docs/source/model_doc/mt5.mdx → docs/source/en/model_doc/mt5.mdx
diff --git a/docs/source/model_doc/nystromformer.mdx → docs/source/en/model_doc/nystromformer.mdx b/docs/source/model_doc/nystromformer.mdx → docs/source/en/model_doc/nystromformer.mdx
diff --git a/docs/source/model_doc/openai-gpt.mdx → docs/source/en/model_doc/openai-gpt.mdx b/docs/source/model_doc/openai-gpt.mdx → docs/source/en/model_doc/openai-gpt.mdx
diff --git a/docs/source/model_doc/pegasus.mdx → docs/source/en/model_doc/pegasus.mdx b/docs/source/model_doc/pegasus.mdx → docs/source/en/model_doc/pegasus.mdx
diff --git a/docs/source/model_doc/perceiver.mdx → docs/source/en/model_doc/perceiver.mdx b/docs/source/model_doc/perceiver.mdx → docs/source/en/model_doc/perceiver.mdx
diff --git a/docs/source/model_doc/phobert.mdx → docs/source/en/model_doc/phobert.mdx b/docs/source/model_doc/phobert.mdx → docs/source/en/model_doc/phobert.mdx
diff --git a/docs/source/model_doc/plbart.mdx → docs/source/en/model_doc/plbart.mdx b/docs/source/model_doc/plbart.mdx → docs/source/en/model_doc/plbart.mdx
diff --git a/docs/source/model_doc/poolformer.mdx → docs/source/en/model_doc/poolformer.mdx b/docs/source/model_doc/poolformer.mdx → docs/source/en/model_doc/poolformer.mdx
diff --git a/docs/source/model_doc/prophetnet.mdx → docs/source/en/model_doc/prophetnet.mdx b/docs/source/model_doc/prophetnet.mdx → docs/source/en/model_doc/prophetnet.mdx
diff --git a/docs/source/model_doc/qdqbert.mdx → docs/source/en/model_doc/qdqbert.mdx b/docs/source/model_doc/qdqbert.mdx → docs/source/en/model_doc/qdqbert.mdx
diff --git a/docs/source/model_doc/rag.mdx → docs/source/en/model_doc/rag.mdx b/docs/source/model_doc/rag.mdx → docs/source/en/model_doc/rag.mdx
diff --git a/docs/source/model_doc/realm.mdx → docs/source/en/model_doc/realm.mdx b/docs/source/model_doc/realm.mdx → docs/source/en/model_doc/realm.mdx
diff --git a/docs/source/model_doc/reformer.mdx → docs/source/en/model_doc/reformer.mdx b/docs/source/model_doc/reformer.mdx → docs/source/en/model_doc/reformer.mdx
diff --git a/docs/source/model_doc/rembert.mdx → docs/source/en/model_doc/rembert.mdx b/docs/source/model_doc/rembert.mdx → docs/source/en/model_doc/rembert.mdx
diff --git a/docs/source/model_doc/resnet.mdx → docs/source/en/model_doc/resnet.mdx b/docs/source/model_doc/resnet.mdx → docs/source/en/model_doc/resnet.mdx
diff --git a/docs/source/model_doc/retribert.mdx → docs/source/en/model_doc/retribert.mdx b/docs/source/model_doc/retribert.mdx → docs/source/en/model_doc/retribert.mdx
diff --git a/docs/source/model_doc/roberta.mdx → docs/source/en/model_doc/roberta.mdx b/docs/source/model_doc/roberta.mdx → docs/source/en/model_doc/roberta.mdx
diff --git a/docs/source/model_doc/roformer.mdx → docs/source/en/model_doc/roformer.mdx b/docs/source/model_doc/roformer.mdx → docs/source/en/model_doc/roformer.mdx
diff --git a/docs/source/model_doc/segformer.mdx → docs/source/en/model_doc/segformer.mdx b/docs/source/model_doc/segformer.mdx → docs/source/en/model_doc/segformer.mdx
diff --git a/docs/source/model_doc/sew-d.mdx → docs/source/en/model_doc/sew-d.mdx b/docs/source/model_doc/sew-d.mdx → docs/source/en/model_doc/sew-d.mdx
diff --git a/docs/source/model_doc/sew.mdx → docs/source/en/model_doc/sew.mdx b/docs/source/model_doc/sew.mdx → docs/source/en/model_doc/sew.mdx
diff --git a/...urce/model_doc/speech-encoder-decoder.mdx → ...e/en/model_doc/speech-encoder-decoder.mdx b/...urce/model_doc/speech-encoder-decoder.mdx → ...e/en/model_doc/speech-encoder-decoder.mdx
diff --git a/docs/source/model_doc/speech_to_text.mdx → docs/source/en/model_doc/speech_to_text.mdx b/docs/source/model_doc/speech_to_text.mdx → docs/source/en/model_doc/speech_to_text.mdx
diff --git a/docs/source/model_doc/speech_to_text_2.mdx → .../source/en/model_doc/speech_to_text_2.mdx b/docs/source/model_doc/speech_to_text_2.mdx → .../source/en/model_doc/speech_to_text_2.mdx
diff --git a/docs/source/model_doc/splinter.mdx → docs/source/en/model_doc/splinter.mdx b/docs/source/model_doc/splinter.mdx → docs/source/en/model_doc/splinter.mdx
diff --git a/docs/source/model_doc/squeezebert.mdx → docs/source/en/model_doc/squeezebert.mdx b/docs/source/model_doc/squeezebert.mdx → docs/source/en/model_doc/squeezebert.mdx
diff --git a/docs/source/model_doc/swin.mdx → docs/source/en/model_doc/swin.mdx b/docs/source/model_doc/swin.mdx → docs/source/en/model_doc/swin.mdx
diff --git a/docs/source/model_doc/t5.mdx → docs/source/en/model_doc/t5.mdx b/docs/source/model_doc/t5.mdx → docs/source/en/model_doc/t5.mdx
diff --git a/docs/source/model_doc/t5v1.1.mdx → docs/source/en/model_doc/t5v1.1.mdx b/docs/source/model_doc/t5v1.1.mdx → docs/source/en/model_doc/t5v1.1.mdx
diff --git a/docs/source/model_doc/tapas.mdx → docs/source/en/model_doc/tapas.mdx b/docs/source/model_doc/tapas.mdx → docs/source/en/model_doc/tapas.mdx
diff --git a/docs/source/model_doc/transfo-xl.mdx → docs/source/en/model_doc/transfo-xl.mdx b/docs/source/model_doc/transfo-xl.mdx → docs/source/en/model_doc/transfo-xl.mdx
diff --git a/docs/source/model_doc/trocr.mdx → docs/source/en/model_doc/trocr.mdx b/docs/source/model_doc/trocr.mdx → docs/source/en/model_doc/trocr.mdx
diff --git a/docs/source/model_doc/unispeech-sat.mdx → docs/source/en/model_doc/unispeech-sat.mdx b/docs/source/model_doc/unispeech-sat.mdx → docs/source/en/model_doc/unispeech-sat.mdx
diff --git a/docs/source/model_doc/unispeech.mdx → docs/source/en/model_doc/unispeech.mdx b/docs/source/model_doc/unispeech.mdx → docs/source/en/model_doc/unispeech.mdx
diff --git a/docs/source/model_doc/van.mdx → docs/source/en/model_doc/van.mdx b/docs/source/model_doc/van.mdx → docs/source/en/model_doc/van.mdx
diff --git a/docs/source/model_doc/vilt.mdx → docs/source/en/model_doc/vilt.mdx b/docs/source/model_doc/vilt.mdx → docs/source/en/model_doc/vilt.mdx
diff --git a/...urce/model_doc/vision-encoder-decoder.mdx → ...e/en/model_doc/vision-encoder-decoder.mdx b/...urce/model_doc/vision-encoder-decoder.mdx → ...e/en/model_doc/vision-encoder-decoder.mdx
diff --git a/...ce/model_doc/vision-text-dual-encoder.mdx → ...en/model_doc/vision-text-dual-encoder.mdx b/...ce/model_doc/vision-text-dual-encoder.mdx → ...en/model_doc/vision-text-dual-encoder.mdx
diff --git a/docs/source/model_doc/visual_bert.mdx → docs/source/en/model_doc/visual_bert.mdx b/docs/source/model_doc/visual_bert.mdx → docs/source/en/model_doc/visual_bert.mdx
diff --git a/docs/source/model_doc/vit.mdx → docs/source/en/model_doc/vit.mdx b/docs/source/model_doc/vit.mdx → docs/source/en/model_doc/vit.mdx
diff --git a/docs/source/model_doc/vit_mae.mdx → docs/source/en/model_doc/vit_mae.mdx b/docs/source/model_doc/vit_mae.mdx → docs/source/en/model_doc/vit_mae.mdx
diff --git a/docs/source/model_doc/wav2vec2.mdx → docs/source/en/model_doc/wav2vec2.mdx b/docs/source/model_doc/wav2vec2.mdx → docs/source/en/model_doc/wav2vec2.mdx
diff --git a/docs/source/model_doc/wav2vec2_phoneme.mdx → .../source/en/model_doc/wav2vec2_phoneme.mdx b/docs/source/model_doc/wav2vec2_phoneme.mdx → .../source/en/model_doc/wav2vec2_phoneme.mdx
diff --git a/docs/source/model_doc/wavlm.mdx → docs/source/en/model_doc/wavlm.mdx b/docs/source/model_doc/wavlm.mdx → docs/source/en/model_doc/wavlm.mdx
diff --git a/docs/source/model_doc/xglm.mdx → docs/source/en/model_doc/xglm.mdx b/docs/source/model_doc/xglm.mdx → docs/source/en/model_doc/xglm.mdx
diff --git a/docs/source/model_doc/xlm-prophetnet.mdx → docs/source/en/model_doc/xlm-prophetnet.mdx b/docs/source/model_doc/xlm-prophetnet.mdx → docs/source/en/model_doc/xlm-prophetnet.mdx
diff --git a/docs/source/model_doc/xlm-roberta-xl.mdx → docs/source/en/model_doc/xlm-roberta-xl.mdx b/docs/source/model_doc/xlm-roberta-xl.mdx → docs/source/en/model_doc/xlm-roberta-xl.mdx
diff --git a/docs/source/model_doc/xlm-roberta.mdx → docs/source/en/model_doc/xlm-roberta.mdx b/docs/source/model_doc/xlm-roberta.mdx → docs/source/en/model_doc/xlm-roberta.mdx
diff --git a/docs/source/model_doc/xlm.mdx → docs/source/en/model_doc/xlm.mdx b/docs/source/model_doc/xlm.mdx → docs/source/en/model_doc/xlm.mdx
diff --git a/docs/source/model_doc/xlnet.mdx → docs/source/en/model_doc/xlnet.mdx b/docs/source/model_doc/xlnet.mdx → docs/source/en/model_doc/xlnet.mdx
diff --git a/docs/source/model_doc/xls_r.mdx → docs/source/en/model_doc/xls_r.mdx b/docs/source/model_doc/xls_r.mdx → docs/source/en/model_doc/xls_r.mdx
diff --git a/docs/source/model_doc/xlsr_wav2vec2.mdx → docs/source/en/model_doc/xlsr_wav2vec2.mdx b/docs/source/model_doc/xlsr_wav2vec2.mdx → docs/source/en/model_doc/xlsr_wav2vec2.mdx
diff --git a/docs/source/model_doc/yoso.mdx → docs/source/en/model_doc/yoso.mdx b/docs/source/model_doc/yoso.mdx → docs/source/en/model_doc/yoso.mdx
diff --git a/docs/source/model_sharing.mdx → docs/source/en/model_sharing.mdx b/docs/source/model_sharing.mdx → docs/source/en/model_sharing.mdx
diff --git a/docs/source/model_summary.mdx → docs/source/en/model_summary.mdx b/docs/source/model_summary.mdx → docs/source/en/model_summary.mdx
diff --git a/docs/source/multilingual.mdx → docs/source/en/multilingual.mdx b/docs/source/multilingual.mdx → docs/source/en/multilingual.mdx
diff --git a/docs/source/en/notebooks.md b/docs/source/en/notebooks.md
@@ -0,0 +1 @@
+../../../notebooks/README.md
diff --git a/docs/source/pad_truncation.mdx → docs/source/en/pad_truncation.mdx b/docs/source/pad_truncation.mdx → docs/source/en/pad_truncation.mdx
diff --git a/docs/source/parallelism.mdx → docs/source/en/parallelism.mdx b/docs/source/parallelism.mdx → docs/source/en/parallelism.mdx
diff --git a/docs/source/performance.mdx → docs/source/en/performance.mdx b/docs/source/performance.mdx → docs/source/en/performance.mdx
diff --git a/docs/source/perplexity.mdx → docs/source/en/perplexity.mdx b/docs/source/perplexity.mdx → docs/source/en/perplexity.mdx
diff --git a/docs/source/philosophy.mdx → docs/source/en/philosophy.mdx b/docs/source/philosophy.mdx → docs/source/en/philosophy.mdx
diff --git a/docs/source/pipeline_tutorial.mdx → docs/source/en/pipeline_tutorial.mdx b/docs/source/pipeline_tutorial.mdx → docs/source/en/pipeline_tutorial.mdx
diff --git a/docs/source/pr_checks.mdx → docs/source/en/pr_checks.mdx b/docs/source/pr_checks.mdx → docs/source/en/pr_checks.mdx
diff --git a/docs/source/preprocessing.mdx → docs/source/en/preprocessing.mdx b/docs/source/preprocessing.mdx → docs/source/en/preprocessing.mdx
diff --git a/docs/source/quicktour.mdx → docs/source/en/quicktour.mdx b/docs/source/quicktour.mdx → docs/source/en/quicktour.mdx
diff --git a/docs/source/run_scripts.mdx → docs/source/en/run_scripts.mdx b/docs/source/run_scripts.mdx → docs/source/en/run_scripts.mdx
diff --git a/docs/source/sagemaker.mdx → docs/source/en/sagemaker.mdx b/docs/source/sagemaker.mdx → docs/source/en/sagemaker.mdx
diff --git a/docs/source/serialization.mdx → docs/source/en/serialization.mdx b/docs/source/serialization.mdx → docs/source/en/serialization.mdx
diff --git a/docs/source/task_summary.mdx → docs/source/en/task_summary.mdx b/docs/source/task_summary.mdx → docs/source/en/task_summary.mdx
diff --git a/docs/source/tasks/asr.mdx → docs/source/en/tasks/asr.mdx b/docs/source/tasks/asr.mdx → docs/source/en/tasks/asr.mdx
diff --git a/docs/source/tasks/audio_classification.mdx → .../source/en/tasks/audio_classification.mdx b/docs/source/tasks/audio_classification.mdx → .../source/en/tasks/audio_classification.mdx
diff --git a/docs/source/tasks/image_classification.mdx → .../source/en/tasks/image_classification.mdx b/docs/source/tasks/image_classification.mdx → .../source/en/tasks/image_classification.mdx
diff --git a/docs/source/tasks/language_modeling.mdx → docs/source/en/tasks/language_modeling.mdx b/docs/source/tasks/language_modeling.mdx → docs/source/en/tasks/language_modeling.mdx
diff --git a/docs/source/tasks/multiple_choice.mdx → docs/source/en/tasks/multiple_choice.mdx b/docs/source/tasks/multiple_choice.mdx → docs/source/en/tasks/multiple_choice.mdx
diff --git a/docs/source/tasks/question_answering.mdx → docs/source/en/tasks/question_answering.mdx b/docs/source/tasks/question_answering.mdx → docs/source/en/tasks/question_answering.mdx
diff --git a/.../source/tasks/sequence_classification.mdx → ...urce/en/tasks/sequence_classification.mdx b/.../source/tasks/sequence_classification.mdx → ...urce/en/tasks/sequence_classification.mdx
diff --git a/docs/source/tasks/summarization.mdx → docs/source/en/tasks/summarization.mdx b/docs/source/tasks/summarization.mdx → docs/source/en/tasks/summarization.mdx
diff --git a/docs/source/tasks/token_classification.mdx → .../source/en/tasks/token_classification.mdx b/docs/source/tasks/token_classification.mdx → .../source/en/tasks/token_classification.mdx
diff --git a/docs/source/tasks/translation.mdx → docs/source/en/tasks/translation.mdx b/docs/source/tasks/translation.mdx → docs/source/en/tasks/translation.mdx
diff --git a/docs/source/testing.mdx → docs/source/en/testing.mdx b/docs/source/testing.mdx → docs/source/en/testing.mdx
diff --git a/docs/source/tokenizer_summary.mdx → docs/source/en/tokenizer_summary.mdx b/docs/source/tokenizer_summary.mdx → docs/source/en/tokenizer_summary.mdx
diff --git a/docs/source/training.mdx → docs/source/en/training.mdx b/docs/source/training.mdx → docs/source/en/training.mdx
diff --git a/docs/source/troubleshooting.mdx → docs/source/en/troubleshooting.mdx b/docs/source/troubleshooting.mdx → docs/source/en/troubleshooting.mdx
diff --git a/docs/source/es/_config.py b/docs/source/es/_config.py
@@ -0,0 +1,14 @@
+# docstyle-ignore
+INSTALL_CONTENT = """
+# Transformers installation
+! pip install transformers datasets
+# To install from source instead of the last release, comment the command above and uncomment the following one.
+# ! pip install git+https://github.com/huggingface/transformers.git
+"""
+
+notebook_first_cells = [{"type": "code", "content": INSTALL_CONTENT}]
+black_avoid_patterns = {
+    "{processor_class}": "FakeProcessorClass",
+    "{model_class}": "FakeModelClass",
+    "{object_class}": "FakeObjectClass",    
+}
diff --git a/docs/source/es/_toctree.yml b/docs/source/es/_toctree.yml
@@ -0,0 +1,17 @@
+- sections: 
+  - local: quicktour
+    title: Quick tour
+  - local: installation
+    title: Instalación
+  title: Get started
+- sections:
+  - local: pipeline_tutorial
+    title: Pipelines para inferencia
+  - local: training
+    title: Fine-tuning a un modelo pre-entrenado
+  - local: accelerate
+    title: Entrenamiento distribuido con 🤗 Accelerate
+  title: Tutorials
+- sections:
+  - local: multilingual
+    title: Modelos multilingües para inferencia
diff --git a/docs/source_es/accelerate.mdx → docs/source/es/accelerate.mdx b/docs/source_es/accelerate.mdx → docs/source/es/accelerate.mdx
diff --git a/docs/source_es/installation.mdx → docs/source/es/installation.mdx b/docs/source_es/installation.mdx → docs/source/es/installation.mdx
@@ -185,43 +185,43 @@ Otra opción para usar 🤗 Transformers offline es descargando previamente los
 * Utiliza el flujo de [`PreTrainedModel.from_pretrained`] y [`PreTrainedModel.save_pretrained`]:
     1. Descarga previamente los archivos con [`PreTrainedModel.from_pretrained`]:
 
-        ```py
-                    >>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+    ```py
+    >>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-        >>> tokenizer = AutoTokenizer.from_pretrained("bigscience/T0_3B")
-        >>> model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/T0_3B")
-        ```
+    >>> tokenizer = AutoTokenizer.from_pretrained("bigscience/T0_3B")
+    >>> model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/T0_3B")
+    ```
 
 
     2. Guarda los archivos en un directorio específico con [`PreTrainedModel.save_pretrained`]:
 
     ```py
-     >>> tokenizer.save_pretrained("./your/path/bigscience_t0")
-     >>> model.save_pretrained("./your/path/bigscience_t0")
-     ```
+    >>> tokenizer.save_pretrained("./your/path/bigscience_t0")
+    >>> model.save_pretrained("./your/path/bigscience_t0")
+    ```
 
     3. Cuando te encuentres offline, recarga los archivos con [`PreTrainedModel.from_pretrained`] desde el directorio especificado: 
 
     ```py
-     >>> tokenizer = AutoTokenizer.from_pretrained("./your/path/bigscience_t0")
-     >>> model = AutoModel.from_pretrained("./your/path/bigscience_t0")
-     ```
+    >>> tokenizer = AutoTokenizer.from_pretrained("./your/path/bigscience_t0")
+    >>> model = AutoModel.from_pretrained("./your/path/bigscience_t0")
+    ```
 
 * Descarga de manera programática los archivos con la biblioteca [huggingface_hub](https://github.com/huggingface/huggingface_hub/tree/main/src/huggingface_hub):
 
     1. Instala la biblioteca [huggingface_hub](https://github.com/huggingface/huggingface_hub/tree/main/src/huggingface_hub) en tu entorno virtual: 
 
     ```bash
-      python -m pip install huggingface_hub
-     ```
+    python -m pip install huggingface_hub
+    ```
 
     2. Utiliza la función [`hf_hub_download`](https://huggingface.co/docs/hub/adding-a-library#download-files-from-the-hub) para descargar un archivo a un path específico. Por ejemplo, el siguiente comando descarga el archivo `config.json` del modelo [T0](https://huggingface.co/bigscience/T0_3B) al path deseado:
 
     ```py
-     >>> from huggingface_hub import hf_hub_download
+    >>> from huggingface_hub import hf_hub_download
 
-     >>> hf_hub_download(repo_id="bigscience/T0_3B", filename="config.json", cache_dir="./your/path/bigscience_t0")
-     ```
+    >>> hf_hub_download(repo_id="bigscience/T0_3B", filename="config.json", cache_dir="./your/path/bigscience_t0")
+    ```
 
 Una vez que el archivo se descargue y se almacene en caché localmente, especifica tu ruta local para cargarlo y usarlo:
 
@@ -236,9 +236,3 @@ Una vez que el archivo se descargue y se almacene en caché localmente, especifi
 Para más detalles sobre cómo descargar archivos almacenados en el Hub consulta la sección [How to download files from the Hub](https://huggingface.co/docs/hub/how-to-downstream).
 
 </Tip>
-
-
-
-
-
-
diff --git a/docs/source_es/multilingual.mdx → docs/source/es/multilingual.mdx b/docs/source_es/multilingual.mdx → docs/source/es/multilingual.mdx
diff --git a/docs/source_es/pipeline_tutorial.mdx → docs/source/es/pipeline_tutorial.mdx b/docs/source_es/pipeline_tutorial.mdx → docs/source/es/pipeline_tutorial.mdx
diff --git a/docs/source_es/quicktour.mdx → docs/source/es/quicktour.mdx b/docs/source_es/quicktour.mdx → docs/source/es/quicktour.mdx
diff --git a/docs/source_es/training.mdx → docs/source/es/training.mdx b/docs/source_es/training.mdx → docs/source/es/training.mdx
diff --git a/docs/source/notebooks.md b/docs/source/notebooks.md
diff --git a/src/transformers/commands/add_new_model.py b/src/transformers/commands/add_new_model.py
@@ -178,7 +178,7 @@ def remove_copy_lines(path):
 
         shutil.move(
             f"{directory}/{lowercase_model_name}.mdx",
-            f"{path_to_transformer_root}/docs/source/model_doc/{lowercase_model_name}.mdx",
+            f"{path_to_transformer_root}/docs/source/en/model_doc/{lowercase_model_name}.mdx",
         )
 
         shutil.move(

diff --git a/src/transformers/commands/add_new_model_like.py b/src/transformers/commands/add_new_model_like.py
@@ -541,7 +541,7 @@ def get_model_files(model_type: str, frameworks: Optional[List[str]] = None) ->
     model_files = list(model_module.glob("*.py"))
     model_files = filter_framework_files(model_files, frameworks=frameworks)
 
-    doc_file = REPO_PATH / "docs" / "source" / "model_doc" / f"{model_type}.mdx"
+    doc_file = REPO_PATH / "docs" / "source" / "en" / "model_doc" / f"{model_type}.mdx"
 
     # Basic pattern for test files
     test_files = [
@@ -1256,7 +1256,7 @@ def disable_fx_test(filename: Path) -> bool:
     add_model_to_auto_classes(old_model_patterns, new_model_patterns, model_classes)
 
     # 5. Add doc file
-    doc_file = REPO_PATH / "docs" / "source" / "model_doc" / f"{old_model_patterns.model_type}.mdx"
+    doc_file = REPO_PATH / "docs" / "source" / "en" / "model_doc" / f"{old_model_patterns.model_type}.mdx"
     duplicate_doc_file(doc_file, old_model_patterns, new_model_patterns, frameworks=frameworks)
 
     # 6. Warn the user for duplicate patterns

diff --git a/utils/check_copies.py b/utils/check_copies.py
@@ -25,7 +25,7 @@
 # All paths are set with the intent you should run this script from the root of the repo with the command
 # python utils/check_copies.py
 TRANSFORMERS_PATH = "src/transformers"
-PATH_TO_DOCS = "docs/source"
+PATH_TO_DOCS = "docs/source/en"
 REPO_PATH = "."
 
 # Mapping for files that are full copies of others (keys are copies, values the file to keep them up to data with)

diff --git a/utils/check_repo.py b/utils/check_repo.py
@@ -31,7 +31,7 @@
 # python utils/check_repo.py
 PATH_TO_TRANSFORMERS = "src/transformers"
 PATH_TO_TESTS = "tests"
-PATH_TO_DOC = "docs/source"
+PATH_TO_DOC = "docs/source/en"
 
 # Update this list with models that are supposed to be private.
 PRIVATE_MODELS = [

diff --git a/utils/check_table.py b/utils/check_table.py
@@ -23,7 +23,7 @@
 # All paths are set with the intent you should run this script from the root of the repo with the command
 # python utils/check_table.py
 TRANSFORMERS_PATH = "src/transformers"
-PATH_TO_DOCS = "docs/source"
+PATH_TO_DOCS = "docs/source/en"
 REPO_PATH = "."