Yaxin
/
live-digital-avatar-gptsovits
25
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

修改文档 (#1521)

Browse Source
main
ChasonJiang 12 months ago committed by GitHub
parent a7e38f93f1
commit 2a9512a63e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File

2
GPT_SoVITS/TTS_infer_pack/TTS.py
Unescape Escape View File

@ -637,7 +637,7 @@ class TTS:
"text": "", # str.(required) text to be synthesized "text": "", # str.(required) text to be synthesized
"text_lang: "", # str.(required) language of the text to be synthesized "text_lang: "", # str.(required) language of the text to be synthesized
"ref_audio_path": "", # str.(required) reference audio path "ref_audio_path": "", # str.(required) reference audio path
"aux_ref_audio_paths": [], # list.(optional) auxiliary reference audio paths for multi-speaker synthesis "aux_ref_audio_paths": [], # list.(optional) auxiliary reference audio paths for multi-speaker tone fusion
"prompt_text": "", # str.(optional) prompt text for the reference audio "prompt_text": "", # str.(optional) prompt text for the reference audio
"prompt_lang": "", # str.(required) language of the prompt text for the reference audio "prompt_lang": "", # str.(required) language of the prompt text for the reference audio
"top_k": 5, # int. top k sampling "top_k": 5, # int. top k sampling

6
api_v2.py
Unescape Escape View File

@ -24,7 +24,7 @@ POST:
"text": "", # str.(required) text to be synthesized "text": "", # str.(required) text to be synthesized
"text_lang: "", # str.(required) language of the text to be synthesized "text_lang: "", # str.(required) language of the text to be synthesized
"ref_audio_path": "", # str.(required) reference audio path "ref_audio_path": "", # str.(required) reference audio path
"aux_ref_audio_paths": [], # list.(optional) auxiliary reference audio paths for multi-speaker synthesis "aux_ref_audio_paths": [], # list.(optional) auxiliary reference audio paths for multi-speaker tone fusion
"prompt_text": "", # str.(optional) prompt text for the reference audio "prompt_text": "", # str.(optional) prompt text for the reference audio
"prompt_lang": "", # str.(required) language of the prompt text for the reference audio "prompt_lang": "", # str.(required) language of the prompt text for the reference audio
"top_k": 5, # int. top k sampling "top_k": 5, # int. top k sampling
@ -34,7 +34,6 @@ POST:
"batch_size": 1, # int. batch size for inference "batch_size": 1, # int. batch size for inference
"batch_threshold": 0.75, # float. threshold for batch splitting. "batch_threshold": 0.75, # float. threshold for batch splitting.
"split_bucket: True, # bool. whether to split the batch into multiple buckets. "split_bucket: True, # bool. whether to split the batch into multiple buckets.
"return_fragment": False, # bool. step by step return the audio fragment.
"speed_factor":1.0, # float. control the speed of the synthesized audio. "speed_factor":1.0, # float. control the speed of the synthesized audio.
"streaming_mode": False, # bool. whether to return a streaming response. "streaming_mode": False, # bool. whether to return a streaming response.
"seed": -1, # int. random seed for reproducibility. "seed": -1, # int. random seed for reproducibility.
@ -302,13 +301,14 @@ async def tts_handle(req:dict):
""" """
streaming_mode = req.get("streaming_mode", False) streaming_mode = req.get("streaming_mode", False)
return_fragment = req.get("return_fragment", False)
media_type = req.get("media_type", "wav") media_type = req.get("media_type", "wav")
check_res = check_params(req) check_res = check_params(req)
if check_res is not None: if check_res is not None:
return check_res return check_res
if streaming_mode: if streaming_mode or return_fragment:
req["return_fragment"] = True req["return_fragment"] = True
try: try:

Write Preview
Loading…
Cancel
Save