gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2026-01-07 02:24:51 -08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #147 from cocktailpeanut/main

Browse Source 
allow multiple audio files for finetune UI
This commit is contained in:
Yushen CHEN
2024-10-18 02:55:42 +08:00
committed by GitHub
parent 39a513e9dd a77c244a16
commit 12304bfafa
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
finetune_gradio.py
View File

@@ -339,7 +339,7 @@ def transcribe(file_audio,language="english"):
)["text"].strip()
return text_transcribe
def transcribe_all(name_project,audio_file,language,user=False,progress=gr.Progress()):
def transcribe_all(name_project,audio_files,language,user=False,progress=gr.Progress()):
name_project+="_pinyin"
path_project= os.path.join(path_data,name_project)
path_dataset = os.path.join(path_project,"dataset")
@@ -357,7 +357,7 @@ def transcribe_all(name_project,audio_file,language,user=False,progress=gr.Progr
if user:
file_audios = [file for format in ('*.wav', '*.ogg', '*.opus', '*.mp3', '*.flac') for file in glob(os.path.join(path_dataset, format))]
else:
file_audios = [audio_file]
file_audios = audio_files
print([file_audios])
@@ -580,7 +580,7 @@ with gr.Blocks() as app:
...
```""",visible=False)
audio_speaker = gr.Audio(label="voice",type="filepath")
audio_speaker = gr.File(label="voice",type="filepath",file_count="multiple")
txt_lang = gr.Text(label="Language",value="english")
bt_transcribe=bt_create=gr.Button("transcribe")
txt_info_transcribe=gr.Text(label="info",value="")
@@ -686,4 +686,4 @@ if __name__ == "__main__":
#transcribe_all(name)
#create_metadata(name)
main()
main()