Merge pull request PaddlePaddle#2138 from zh794390558/demos

[demos] more cli for speech demos

demos/speech_recognition/run.sh

@@ -1,10 +1,26 @@
 #!/bin/bash
 
-wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
+wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
+wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
 
 # asr
 paddlespeech asr --input ./zh.wav
 
 
 # asr + punc
 paddlespeech asr --input ./zh.wav | paddlespeech text --task punc
+
+
+# asr help
+paddlespeech asr --help
+
+
+# english asr
+paddlespeech asr --lang en --model transformer_librispeech --input ./en.wav
+
+# model stats
+paddlespeech stats --task asr
+
+
+# paddlespeech help
+paddlespeech --help

demos/speech_server/server.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 
-paddlespeech_server start --config_file ./conf/application.yaml
+paddlespeech_server start --config_file ./conf/application.yaml &> server.log &

demos/speech_server/sid_client.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+wget -c https://paddlespeech.bj.bcebos.com/vector/audio/85236145389.wav
+wget -c https://paddlespeech.bj.bcebos.com/vector/audio/123456789.wav
+
+# sid extract
+paddlespeech_client vector --server_ip 127.0.0.1 --port 8090 --task spk --input ./85236145389.wav
+
+# sid score
+paddlespeech_client vector --server_ip 127.0.0.1 --port 8090 --task score --enroll ./85236145389.wav --test ./123456789.wav

demos/speech_server/text_client.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+
+paddlespeech_client text --server_ip 127.0.0.1 --port 8090 --input 今天的天气真好啊你下午有空吗我想约你一起去吃饭

demos/streaming_asr_server/server.sh

@@ -1,9 +1,8 @@
-export CUDA_VISIBLE_DEVICE=0,1,2,3
- export CUDA_VISIBLE_DEVICE=0,1,2,3
+#export CUDA_VISIBLE_DEVICE=0,1,2,3
 
-# nohup python3 punc_server.py --config_file conf/punc_application.yaml > punc.log 2>&1 &
+# nohup python3 local/punc_server.py --config_file conf/punc_application.yaml > punc.log 2>&1 &
 paddlespeech_server start --config_file conf/punc_application.yaml &> punc.log &
 
-# nohup python3 streaming_asr_server.py --config_file conf/ws_conformer_wenetspeech_application.yaml > streaming_asr.log 2>&1 &
+# nohup python3 local/streaming_asr_server.py --config_file conf/ws_conformer_wenetspeech_application.yaml > streaming_asr.log 2>&1 &
 paddlespeech_server start --config_file conf/ws_conformer_wenetspeech_application.yaml &> streaming_asr.log  &
 

demos/streaming_asr_server/test.sh

@@ -7,5 +7,5 @@ paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wa
 
 # read the wav and call streaming and punc service
 # If `127.0.0.1` is not accessible, you need to use the actual service IP address.
-paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav
+paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav
 

demos/streaming_tts_server/test_client.sh → demos/streaming_tts_server/client.sh

@@ -2,8 +2,8 @@
 
 # http client test
 # If `127.0.0.1` is not accessible, you need to use the actual service IP address.
-paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
+paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.http.wav
 
 # websocket client test
 # If `127.0.0.1` is not accessible, you need to use the actual service IP address.
-# paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
+paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8192 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.ws.wav

demos/streaming_tts_server/conf/tts_online_ws_application.yaml

@@ -0,0 +1,103 @@
+# This is the parameter configuration file for streaming tts server.
+
+#################################################################################
+#                             SERVER SETTING                                    #
+#################################################################################
+host: 0.0.0.0
+port: 8192
+
+# The task format in the engin_list is: <speech task>_<engine type>
+# engine_list choices = ['tts_online', 'tts_online-onnx'], the inference speed of tts_online-onnx is faster than tts_online.
+# protocol choices = ['websocket', 'http'] 
+protocol: 'websocket'
+engine_list: ['tts_online-onnx']
+
+
+#################################################################################
+#                                ENGINE CONFIG                                  #
+#################################################################################
+
+################################### TTS #########################################
+################### speech task: tts; engine_type: online #######################
+tts_online: 
+    # am (acoustic model) choices=['fastspeech2_csmsc', 'fastspeech2_cnndecoder_csmsc']   
+    # fastspeech2_cnndecoder_csmsc support streaming am infer.     
+    am: 'fastspeech2_csmsc'   
+    am_config: 
+    am_ckpt: 
+    am_stat: 
+    phones_dict: 
+    tones_dict: 
+    speaker_dict: 
+    spk_id: 0
+
+    # voc (vocoder) choices=['mb_melgan_csmsc, hifigan_csmsc']
+    # Both mb_melgan_csmsc and hifigan_csmsc support streaming voc inference
+    voc: 'mb_melgan_csmsc'
+    voc_config: 
+    voc_ckpt: 
+    voc_stat: 
+
+    # others
+    lang: 'zh'
+    device: 'cpu' # set 'gpu:id' or 'cpu'
+    # am_block and am_pad only for fastspeech2_cnndecoder_onnx model to streaming am infer,
+    # when am_pad set 12, streaming synthetic audio is the same as non-streaming synthetic audio
+    am_block: 72
+    am_pad: 12
+    # voc_pad and voc_block voc model to streaming voc infer,
+    # when voc model is mb_melgan_csmsc, voc_pad set 14, streaming synthetic audio is the same as non-streaming synthetic audio; The minimum value of pad can be set to 7, streaming synthetic audio sounds normal
+    # when voc model is hifigan_csmsc, voc_pad set 19, streaming synthetic audio is the same as non-streaming synthetic audio; voc_pad set 14, streaming synthetic audio sounds normal
+    voc_block: 36
+    voc_pad: 14
+
+
+
+#################################################################################
+#                                ENGINE CONFIG                                  #
+#################################################################################
+
+################################### TTS #########################################
+################### speech task: tts; engine_type: online-onnx #######################
+tts_online-onnx: 
+    # am (acoustic model) choices=['fastspeech2_csmsc_onnx', 'fastspeech2_cnndecoder_csmsc_onnx']
+    # fastspeech2_cnndecoder_csmsc_onnx support streaming am infer.        
+    am: 'fastspeech2_cnndecoder_csmsc_onnx' 
+    # am_ckpt is a list, if am is fastspeech2_cnndecoder_csmsc_onnx, am_ckpt = [encoder model, decoder model, postnet model];
+    # if am is fastspeech2_csmsc_onnx, am_ckpt = [ckpt model];
+    am_ckpt:   # list
+    am_stat: 
+    phones_dict: 
+    tones_dict: 
+    speaker_dict: 
+    spk_id: 0
+    am_sample_rate: 24000
+    am_sess_conf:
+        device: "cpu" # set 'gpu:id' or 'cpu'
+        use_trt: False
+        cpu_threads: 4
+
+    # voc (vocoder) choices=['mb_melgan_csmsc_onnx, hifigan_csmsc_onnx']
+    # Both mb_melgan_csmsc_onnx and hifigan_csmsc_onnx support streaming voc inference
+    voc: 'hifigan_csmsc_onnx'
+    voc_ckpt: 
+    voc_sample_rate: 24000
+    voc_sess_conf:
+        device: "cpu" # set 'gpu:id' or 'cpu'
+        use_trt: False
+        cpu_threads: 4
+
+    # others
+    lang: 'zh'
+    # am_block and am_pad only for fastspeech2_cnndecoder_onnx model to streaming am infer,
+    # when am_pad set 12, streaming synthetic audio is the same as non-streaming synthetic audio
+    am_block: 72
+    am_pad: 12
+    # voc_pad and voc_block voc model to streaming voc infer,
+    # when voc model is mb_melgan_csmsc_onnx, voc_pad set 14, streaming synthetic audio is the same as non-streaming synthetic audio; The minimum value of pad can be set to 7, streaming synthetic audio sounds normal
+    # when voc model is hifigan_csmsc_onnx, voc_pad set 19, streaming synthetic audio is the same as non-streaming synthetic audio; voc_pad set 14, streaming synthetic audio sounds normal
+    voc_block: 36
+    voc_pad: 14
+    # voc_upsample should be same as n_shift on voc config.
+    voc_upsample: 300
+

demos/streaming_tts_server/server.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# http server
+paddlespeech_server start --config_file ./conf/tts_online_application.yaml &> tts.http.log &
+
+
+# websocket server
+paddlespeech_server start --config_file ./conf/tts_online_ws_application.yaml &> tts.ws.log &
+
+

demos/text_to_speech/run.sh

@@ -4,4 +4,10 @@
 paddlespeech tts --input 今天的天气不错啊
 
 # Batch process
-echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts
+echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts
+
+# Text Frontend
+paddlespeech tts --input 今天是2022/10/29,最低温度是-3℃.
+
+
+

paddlespeech/server/bin/paddlespeech_client.py

@@ -718,6 +718,7 @@ def __call__(self,
             logger.info(f"the input audio: {input}")
             handler = VectorHttpHandler(server_ip=server_ip, port=port)
             res = handler.run(input, audio_format, sample_rate)
+            logger.info(f"The spk embedding is: {res}")
             return res
         elif task == "score":
             from paddlespeech.server.utils.audio_handler import VectorScoreHttpHandler