tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into dev

Browse Source
This commit is contained in:
litagin02
2024-01-17 10:23:29 +09:00
parent a24d997730 eff8821d65
commit c0085e4fcb
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
transcribe.py
View File

@@ -66,17 +66,19 @@ if __name__ == "__main__":
os.rename(output_file, output_file + ".bak") os.rename(output_file, output_file + ".bak")
if language == "ja": if language == "ja":
language_id = Languages.JP language_id = Languages.JP.value
elif language == "en": elif language == "en":
language_id = Languages.EN language_id = Languages.EN.value
elif language == "zh": elif language == "zh":
language_id = Languages.ZH language_id = Languages.ZH.value
else: else:
raise ValueError(f"{language} is not supported.") raise ValueError(f"{language} is not supported.")
with open(output_file, "w", encoding="utf-8") as f: with open(output_file, "w", encoding="utf-8") as f:
for wav_file in tqdm(wav_files, file=SAFE_STDOUT): for wav_file in tqdm(wav_files, file=SAFE_STDOUT):
file_name = os.path.basename(wav_file) file_name = os.path.basename(wav_file)
text = transcribe(wav_file, initial_prompt=initial_prompt, language=language) text = transcribe(
wav_file, initial_prompt=initial_prompt, language=language
)
f.write(f"{file_name}|{speaker_name}|{language_id}|{text}\n") f.write(f"{file_name}|{speaker_name}|{language_id}|{text}\n")
f.flush() f.flush()
sys.exit(0) sys.exit(0)