From 74245cc115122e2f1774d720be3c068ee4b52525 Mon Sep 17 00:00:00 2001 From: Hui Zhang Date: Tue, 12 Jul 2022 09:40:48 +0000 Subject: [PATCH] add streaming tts scripts --- demos/streaming_tts_server/client.sh | 9 ++ .../conf/tts_online_ws_application.yaml | 103 ++++++++++++++++++ demos/streaming_tts_server/server.sh | 10 ++ 3 files changed, 122 insertions(+) create mode 100755 demos/streaming_tts_server/client.sh create mode 100644 demos/streaming_tts_server/conf/tts_online_ws_application.yaml create mode 100755 demos/streaming_tts_server/server.sh diff --git a/demos/streaming_tts_server/client.sh b/demos/streaming_tts_server/client.sh new file mode 100755 index 00000000..e93da58a --- /dev/null +++ b/demos/streaming_tts_server/client.sh @@ -0,0 +1,9 @@ +#!/bin/bash + +# 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.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 8192 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.ws.wav diff --git a/demos/streaming_tts_server/conf/tts_online_ws_application.yaml b/demos/streaming_tts_server/conf/tts_online_ws_application.yaml new file mode 100644 index 00000000..146f06f1 --- /dev/null +++ b/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: _ +# 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 + diff --git a/demos/streaming_tts_server/server.sh b/demos/streaming_tts_server/server.sh new file mode 100755 index 00000000..d34ddba0 --- /dev/null +++ b/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 & + +