You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
################################### 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_ljspeech_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:
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_ljspeech_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: 'en'
# 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: 10
# 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: 7
# voc_upsample should be same as n_shift on voc config.
voc_upsample: 300
``
报错信息:
[2024-04-01 07:29:24,459] [ ERROR] - Please check config, am support: fastspeech2, voc support: hifigan_csmsc-zh or mb_melgan_csmsc.
The text was updated successfully, but these errors were encountered:
根据中文的demo改了一下am和voc,启动失败,看报错好像只支持中文流式?下面是我的配置:
``
#################################################################################
SERVER SETTING
#################################################################################
host: 0.0.0.0
port: 8888
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-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_ljspeech_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:
am_sample_rate: 24000
am_sess_conf:
device: "cpu" # set 'gpu:id' or 'cpu'
use_trt: False
cpu_threads: 4
``
报错信息:
[2024-04-01 07:29:24,459] [ ERROR] - Please check config, am support: fastspeech2, voc support: hifigan_csmsc-zh or mb_melgan_csmsc.
The text was updated successfully, but these errors were encountered: