v3ucn / asr_tools_webui Goto Github PK

每次启动都要下一些modelscope的包，如果用了魔法还巨慢，好像反向对海外地址做了限速，这是魔塔的模型吗？

Whisper转写可以调用gpu,很快转写完成
Faster-Whisper则是调用的cpu，很慢

安装好费时。
请帮忙看下，是否能删除一些不须的？

I've tried installing the repo in a python 3.8 environment and many package conflicted.
After switching to python 3.10, the installation finished painlessly.
There might be a minimal version requirement for python.

啊啊啊啊，可恶一回车就发出来了！

不知道为什么新版webui执行操作都是python3，如果你是win系统你会收到一个不知原因的报错，这是因为win环境没有python3
如果你的环境没有python3，你直接把python.exe复制然后把副本改名成python3.exe就可以了

Error: Traceback (most recent call last):
File "F:\Bert-Vits2_Audio_Tool\short_audio_transcribe_whisper.py", line 162, in
text = transcribe_one(f"{input_file}"+wav_file,mytype)
File "F:\Bert-Vits2_Audio_Tool\short_audio_transcribe_whisper.py", line 51, in transcribe_one
audio = whisper.load_audio(audio_path)
File "F:\Bert-Vits2_Audio_Tool\venv\lib\site-packages\whisper\audio.py", line 58, in load_audio
out = run(cmd, capture_output=True, check=True).stdout
File "F:\Bert-Vits2_Audio_Tool\venv\lib\subprocess.py", line 505, in run
with Popen(*popenargs, **kwargs) as process:
File "F:\Bert-Vits2_Audio_Tool\venv\lib\subprocess.py", line 951, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "F:\Bert-Vits2_Audio_Tool\venv\lib\subprocess.py", line 1436, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] 系统找不到指定的文件。