blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-04-05 19:41:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/main' into chores

Browse Source 
merge main
This commit is contained in:
XXXXRT666 2024-08-26 00:49:42 +08:00
commit 9d2ec9a868
3 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
GPT_SoVITS/TTS_infer_pack/TTS.py
View File

@ -642,7 +642,7 @@ class TTS:
"text": "", # str.(required) text to be synthesized
"text_lang: "", # str.(required) language of the text to be synthesized
"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_lang": "", # str.(required) language of the prompt text for the reference audio
"top_k": 5, # int. top k sampling

3
GPT_SoVITS/inference_webui.py
View File

@ -397,7 +397,8 @@ def merge_short_text_in_array(texts, threshold):
##ref_wav_path+prompt_text+prompt_language+text(单个)+text_language+top_k+top_p+temperature
# cache_tokens={}#暂未实现清理机制
cache= {}
def get_tts_wav(ref_wav_path, prompt_text, prompt_language, text, text_language, how_to_cut=i18n("不切"), top_k=20, top_p=0.6, temperature=0.6, ref_free = False,speed=1,if_freeze=False,inp_refs=123):
def get_tts_wav(ref_wav_path, prompt_text, prompt_language, text, text_language, how_to_cut=i18n("不切"), top_k=20, top_p=0.6, temperature=0.6, ref_free
=False,speed=1,if_freeze=False,inp_refs=None):
global cache
if ref_wav_path:pass
else:gr.Warning(i18n('请上传参考音频'))

6
api_v2.py
View File

@ -24,7 +24,7 @@ POST:
"text": "", # str.(required) text to be synthesized
"text_lang: "", # str.(required) language of the text to be synthesized
"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_lang": "", # str.(required) language of the prompt text for the reference audio
"top_k": 5, # int. top k sampling
@ -34,7 +34,6 @@ POST:
"batch_size": 1, # int. batch size for inference
"batch_threshold": 0.75, # float. threshold for batch splitting.
"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.
"streaming_mode": False, # bool. whether to return a streaming response.
"seed": -1, # int. random seed for reproducibility.
@ -302,13 +301,14 @@ async def tts_handle(req:dict):
"""
streaming_mode = req.get("streaming_mode", False)
return_fragment = req.get("return_fragment", False)
media_type = req.get("media_type", "wav")
check_res = check_params(req)
if check_res is not None:
return check_res
if streaming_mode:
if streaming_mode or return_fragment:
req["return_fragment"] = True
try: