add info, test=doc

demos/streaming_tts_server/README.md

@@ -15,12 +15,21 @@ You can choose one way from meduim and hard to install paddlespeech.
 
 
 ### 2. Prepare config File
-The configuration file can be found in `conf/tts_online_application.yaml` 。
+The configuration file can be found in `conf/tts_online_application.yaml`.
-Among them, `protocol` indicates the network protocol used by the streaming TTS service. Currently, both http and websocket are supported.
+- `protocol` indicates the network protocol used by the streaming TTS service. Currently, both http and websocket are supported.
-`engine_list` indicates the speech engine that will be included in the service to be started, in the format of `<speech task>_<engine type>`.
+- `engine_list` indicates the speech engine that will be included in the service to be started, in the format of `<speech task>_<engine type>`.
-This demo mainly introduces the streaming speech synthesis service, so the speech task should be set to `tts`.
+    - This demo mainly introduces the streaming speech synthesis service, so the speech task should be set to `tts`.
-Currently, the engine type supports two forms: **online**  and **online-onnx**. `online` indicates an engine that uses python for dynamic graph inference; `online-onnx` indicates an engine that uses onnxruntime for inference. The inference speed of online-onnx is faster.
+    - the engine type supports two forms: **online**  and **online-onnx**. `online` indicates an engine that uses python for dynamic graph inference; `online-onnx` indicates an engine that uses onnxruntime for inference. The inference speed of online-onnx is faster.
-Streaming TTS AM model support: **fastspeech2 and fastspeech2_cnndecoder**; Voc model support: **hifigan and mb_melgan**
+- Streaming TTS engine AM model support: **fastspeech2 and fastspeech2_cnndecoder**; Voc model support: **hifigan and mb_melgan**
+- In streaming am inference, one chunk of data is inferred at a time to achieve a streaming effect. Among them, `am_block` indicates the number of valid frames in the chunk, and `am_pad` indicates the number of frames added before and after am_block in a chunk. The existence of am_pad is used to eliminate errors caused by streaming inference and avoid the influence of streaming inference on the quality of synthesized audio.
+    - fastspeech2 does not support streaming am inference, so am_pad and am_block have no effect on it.
+    - fastspeech2_cnndecoder supports streaming inference. When am_pad=12, streaming inference synthesized audio is consistent with non-streaming synthesized audio.
+- In streaming voc inference, one chunk of data is inferred at a time to achieve a streaming effect. Where `voc_block` indicates the number of valid frames in the chunk, and `voc_pad` indicates the number of frames added before and after the voc_block in a chunk. The existence of voc_pad is used to eliminate errors caused by streaming inference and avoid the influence of streaming inference on the quality of synthesized audio.
+    - Both hifigan and mb_melgan support streaming voc inference.
+    - When the voc model is mb_melgan, when voc_pad=14, the synthetic audio for streaming inference is consistent with the non-streaming synthetic audio; the minimum voc_pad can be set to 7, and the synthetic audio has no abnormal hearing. If the voc_pad is less than 7, the synthetic audio sounds abnormal.
+    - When the voc model is hifigan, when voc_pad=20, the streaming inference synthetic audio is consistent with the non-streaming synthetic audio; when voc_pad=14, the synthetic audio has no abnormal hearing.
+- Inference speed: mb_melgan > hifigan; Audio quality: mb_melgan < hifigan
+
 
 
 ### 3. Server Usage

demos/streaming_tts_server/README_cn.md

@@ -16,11 +16,19 @@
 
 ### 2. 准备配置文件
 配置文件可参见 `conf/tts_online_application.yaml` 。
-其中，`protocol`表示该流式TTS服务使用的网络协议，目前支持 http 和 websocket 两种。
+- `protocol`表示该流式TTS服务使用的网络协议，目前支持 http 和 websocket 两种。
-其中，`engine_list`表示即将启动的服务将会包含的语音引擎，格式为 <语音任务>_<引擎类型>。
+- `engine_list`表示即将启动的服务将会包含的语音引擎，格式为 <语音任务>_<引擎类型>。
-该demo主要介绍流式语音合成服务，因此语音任务应设置为tts。
+    - 该demo主要介绍流式语音合成服务，因此语音任务应设置为tts。
-目前引擎类型支持两种形式：**online** 表示使用python进行动态图推理的引擎；**online-onnx** 表示使用onnxruntime进行推理的引擎。其中，online-onnx的推理速度更快。
+    - 目前引擎类型支持两种形式：**online** 表示使用python进行动态图推理的引擎；**online-onnx** 表示使用onnxruntime进行推理的引擎。其中，online-onnx的推理速度更快。
-流式TTS的AM 模型支持：fastspeech2 以及fastspeech2_cnndecoder; Voc 模型支持：hifigan, mb_melgan
+- 流式TTS引擎的AM模型支持：fastspeech2 以及fastspeech2_cnndecoder; Voc 模型支持：hifigan, mb_melgan
+- 流式am推理中，每次会对一个chunk的数据进行推理以达到流式的效果。其中`am_block`表示chunk中的有效帧数，`am_pad` 表示一个chunk中am_block前后各加的帧数。am_pad的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。
+    - fastspeech2不支持流式am推理，因此am_pad与am_block对它无效
+    - fastspeech2_cnndecoder 支持流式推理，当am_pad=12时，流式推理合成音频与非流式合成音频一致
+- 流式voc推理中，每次会对一个chunk的数据进行推理以达到流式的效果。其中`voc_block`表示chunk中的有效帧数，`voc_pad` 表示一个chunk中voc_block前后各加的帧数。voc_pad的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。
+    - hifigan, mb_melgan 均支持流式voc 推理
+    - 当voc模型为mb_melgan，当voc_pad=14时，流式推理合成音频与非流式合成音频一致；voc_pad最小可以设置为7，合成音频听感上没有异常，若voc_pad小于7，合成音频听感上存在异常。
+    - 当voc模型为hifigan，当voc_pad=20时，流式推理合成音频与非流式合成音频一致；当voc_pad=14时，合成音频听感上没有异常。
+- 推理速度：mb_melgan > hifigan; 音频质量：mb_melgan < hifigan
 
 ### 3. 服务端使用方法
 - 命令行 (推荐使用)

demos/streaming_tts_server/conf/tts_online_application.yaml

@@ -1,4 +1,4 @@
-# This is the parameter configuration file for PaddleSpeech Serving.
+# This is the parameter configuration file for streaming tts server.
 
 #################################################################################
 #                             SERVER SETTING                                    #
@@ -7,8 +7,8 @@ host: 127.0.0.1
 port: 8092
 
 # The task format in the engin_list is: <speech task>_<engine type>
-# engine_list choices = ['tts_online', 'tts_online-onnx']
+# engine_list choices = ['tts_online', 'tts_online-onnx'], the inference speed of tts_online-onnx is faster than tts_online.
-# protocol = ['websocket', 'http'] (only one can be selected).
+# protocol choices = ['websocket', 'http'] 
 protocol: 'http'
 engine_list: ['tts_online-onnx']
 
@@ -20,7 +20,8 @@ engine_list: ['tts_online-onnx']
 ################################### TTS #########################################
 ################### speech task: tts; engine_type: online #######################
 tts_online: 
-    # am (acoustic model) choices=['fastspeech2_csmsc', 'fastspeech2_cnndecoder_csmsc']        
+    # am (acoustic model) choices=['fastspeech2_csmsc', 'fastspeech2_cnndecoder_csmsc']   
+    # fastspeech2_cnndecoder_csmsc support streaming am infer.     
     am: 'fastspeech2_csmsc'   
     am_config: 
     am_ckpt: 
@@ -31,6 +32,7 @@ tts_online:
     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: 
@@ -39,8 +41,13 @@ tts_online:
     # 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: 42
     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 20, streaming synthetic audio is the same as non-streaming synthetic audio; voc_pad set 14, streaming synthetic audio sounds normal
     voc_block: 14
     voc_pad: 14
     
@@ -53,7 +60,8 @@ tts_online:
 ################################### TTS #########################################
 ################### speech task: tts; engine_type: online-onnx #######################
 tts_online-onnx: 
-    # am (acoustic model) choices=['fastspeech2_csmsc_onnx', 'fastspeech2_cnndecoder_csmsc_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];
@@ -70,6 +78,7 @@ tts_online-onnx:
         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
@@ -80,9 +89,15 @@ tts_online-onnx:
 
     # 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: 42
     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 20, streaming synthetic audio is the same as non-streaming synthetic audio; voc_pad set 14, streaming synthetic audio sounds normal
     voc_block: 14
     voc_pad: 14
+    # voc_upsample should be same as n_shift on voc config.
     voc_upsample: 300
     

paddlespeech/server/conf/tts_online_application.yaml

@@ -1,4 +1,4 @@
-# This is the parameter configuration file for PaddleSpeech Serving.
+# This is the parameter configuration file for streaming tts server.
 
 #################################################################################
 #                             SERVER SETTING                                    #
@@ -7,8 +7,8 @@ host: 127.0.0.1
 port: 8092
 
 # The task format in the engin_list is: <speech task>_<engine type>
-# task choices = ['tts_online', 'tts_online-onnx']
+# engine_list choices = ['tts_online', 'tts_online-onnx'], the inference speed of tts_online-onnx is faster than tts_online.
-# protocol = ['websocket', 'http'] (only one can be selected).
+# protocol choices = ['websocket', 'http'] 
 protocol: 'http'
 engine_list: ['tts_online-onnx']
 
@@ -20,8 +20,9 @@ engine_list: ['tts_online-onnx']
 ################################### TTS #########################################
 ################### speech task: tts; engine_type: online #######################
 tts_online: 
-    # am (acoustic model) choices=['fastspeech2_csmsc', 'fastspeech2_cnndecoder_csmsc']        
+    # am (acoustic model) choices=['fastspeech2_csmsc', 'fastspeech2_cnndecoder_csmsc']   
-    am: 'fastspeech2_cnndecoder_csmsc'   
+    # fastspeech2_cnndecoder_csmsc support streaming am infer.     
+    am: 'fastspeech2_csmsc'   
     am_config: 
     am_ckpt: 
     am_stat: 
@@ -31,6 +32,7 @@ tts_online:
     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: 
@@ -39,8 +41,13 @@ tts_online:
     # 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: 42
     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 20, streaming synthetic audio is the same as non-streaming synthetic audio; voc_pad set 14, streaming synthetic audio sounds normal
     voc_block: 14
     voc_pad: 14
     
@@ -53,7 +60,8 @@ tts_online:
 ################################### TTS #########################################
 ################### speech task: tts; engine_type: online-onnx #######################
 tts_online-onnx: 
-    # am (acoustic model) choices=['fastspeech2_csmsc_onnx', 'fastspeech2_cnndecoder_csmsc_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];
@@ -70,6 +78,7 @@ tts_online-onnx:
         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
@@ -80,9 +89,15 @@ tts_online-onnx:
 
     # 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: 42
     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 20, streaming synthetic audio is the same as non-streaming synthetic audio; voc_pad set 14, streaming synthetic audio sounds normal
     voc_block: 14
     voc_pad: 14
+    # voc_upsample should be same as n_shift on voc config.
     voc_upsample: 300
     

setup.py

@@ -73,8 +73,6 @@ server = [
     "uvicorn",
     "pattern_singleton",
     "websockets",
-    "websocket",
-    "websocket-client",
 ]
 
 requirements = {