Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[server]replace default vocoder in seerver to mb_melgan, test=doc #2214

Merged
merged 1 commit into from
Aug 2, 2022
Merged

[server]replace default vocoder in seerver to mb_melgan, test=doc #2214

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 11 additions & 9 deletions demos/speech_server/conf/application.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ host: 0.0.0.0
port: 8090

# The task format in the engin_list is: <speech task>_<engine type>
# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference']
# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference', 'text_python', 'vector_python']
protocol: 'http'
engine_list: ['asr_python', 'tts_python', 'cls_python', 'text_python', 'vector_python']

Expand All @@ -28,7 +28,6 @@ asr_python:
force_yes: True
device: # set 'gpu:id' or 'cpu'


################### speech task: asr; engine_type: inference #######################
asr_inference:
# model_type choices=['deepspeech2offline_aishell']
Expand All @@ -50,10 +49,11 @@ asr_inference:

################################### TTS #########################################
################### speech task: tts; engine_type: python #######################
tts_python:
# am (acoustic model) choices=['speedyspeech_csmsc', 'fastspeech2_csmsc',
# 'fastspeech2_ljspeech', 'fastspeech2_aishell3',
# 'fastspeech2_vctk']
tts_python:
# am (acoustic model) choices=['speedyspeech_csmsc', 'fastspeech2_csmsc',
# 'fastspeech2_ljspeech', 'fastspeech2_aishell3',
# 'fastspeech2_vctk', 'fastspeech2_mix',
# 'tacotron2_csmsc', 'tacotron2_ljspeech']
am: 'fastspeech2_csmsc'
am_config:
am_ckpt:
Expand All @@ -64,8 +64,10 @@ tts_python:
spk_id: 0

# voc (vocoder) choices=['pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3',
# 'pwgan_vctk', 'mb_melgan_csmsc']
voc: 'pwgan_csmsc'
# 'pwgan_vctk', 'mb_melgan_csmsc', 'style_melgan_csmsc',
# 'hifigan_csmsc', 'hifigan_ljspeech', 'hifigan_aishell3',
# 'hifigan_vctk', 'wavernn_csmsc']
voc: 'mb_melgan_csmsc'
voc_config:
voc_ckpt:
voc_stat:
Expand Down Expand Up @@ -94,7 +96,7 @@ tts_inference:
summary: True # False -> do not show predictor config

# voc (vocoder) choices=['pwgan_csmsc', 'mb_melgan_csmsc','hifigan_csmsc']
voc: 'pwgan_csmsc'
voc: 'mb_melgan_csmsc'
voc_model: # the pdmodel file of your vocoder static model (XX.pdmodel)
voc_params: # the pdiparams file of your vocoder static model (XX.pdipparams)
voc_sample_rate: 24000
Expand Down
4 changes: 2 additions & 2 deletions demos/streaming_tts_server/conf/tts_online_application.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ tts_online-onnx:

# 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: 'mb_melgan_csmsc_onnx'
voc_ckpt:
voc_sample_rate: 24000
voc_sess_conf:
Expand All @@ -100,4 +100,4 @@ tts_online-onnx:
voc_pad: 14
# voc_upsample should be same as n_shift on voc config.
voc_upsample: 300


4 changes: 2 additions & 2 deletions demos/streaming_tts_server/conf/tts_online_ws_application.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ tts_online-onnx:

# 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: 'mb_melgan_csmsc_onnx'
voc_ckpt:
voc_sample_rate: 24000
voc_sess_conf:
Expand All @@ -100,4 +100,4 @@ tts_online-onnx:
voc_pad: 14
# voc_upsample should be same as n_shift on voc config.
voc_upsample: 300