azalea/VITS-fast-fine-tuning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

updated pipeline

Browse Source
This commit is contained in:
Plachta
2023-02-27 00:22:00 +08:00
parent 4b2ea54c96
commit 03e3894fe4
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
long_audio_transcribe.py
+2 -1
View File
@@ -10,6 +10,7 @@ filelist = list(os.walk(parent_dir))[0][2]
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--languages", default="CJE")
parser.add_argument("--whisper_size", default="medium")
args = parser.parse_args()
if args.languages == "CJE":
lang2token = {
@@ -22,7 +23,7 @@ if __name__ == "__main__":
'zh': "[ZH]",
'ja': "[JA]",
}
model = whisper.load_model("large")
model = whisper.load_model(args.whisper_size)
speaker_annos = []
for file in filelist:
print(f"transcribing {parent_dir + file}...\n")
short_audio_transcribe.py
+2 -1
View File
@@ -30,6 +30,7 @@ def transcribe_one(audio_path):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--languages", default="CJE")
parser.add_argument("--whisper_size", default="medium")
args = parser.parse_args()
if args.languages == "CJE":
lang2token = {
@@ -42,7 +43,7 @@ if __name__ == "__main__":
'zh': "[ZH]",
'ja': "[JA]",
}
model = whisper.load_model("large")
model = whisper.load_model(args.whisper_size)
parent_dir = "./custom_character_voice/"
speaker_names = list(os.walk(parent_dir))[0][1]
speaker_annos = []