F5-TTS V5版 - 更新更强的V1模型，提升推理和训练效果。零样本免训练语音克隆，文本转语音 本地一键整合包下载

zhengu***

谢谢楼主提供辛苦

来日***

很奇怪，我没用补丁，也能运行

财源***

Traceback (most recent call last):
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\gradio\queueing.py", line 625, in process_events
    response = await route_utils.call_process_api(
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
    output = await app.get_blocks().process_api(
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\gradio\blocks.py", line 2051, in process_api
    result = await self.call_function(
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\gradio\blocks.py", line 1598, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 2461, in run_sync_in_worker_thread
    return await future
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 962, in run
    result = context.run(func, *args)
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\gradio\utils.py", line 883, in wrapper
    response = f(*args, **kwargs)
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\src\f5_tts\infer\infer_gradio.py", line 245, in basic_tts
    audio_out, spectrogram_path, ref_text_out = infer(
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\src\f5_tts\infer\infer_gradio.py", line 135, in infer
    ref_audio, ref_text = preprocess_ref_audio_text(ref_audio_orig, ref_text, show_info=show_info)
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\src\f5_tts\infer\utils_infer.py", line 295, in preprocess_ref_audio_text
    aseg = AudioSegment.from_file(ref_audio_orig)
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\pydub\audio_segment.py", line 728, in from_file
    info = mediainfo_json(orig_file, read_ahead_limit=read_ahead_limit)
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site-packages\pydub\utils.py", line 274, in mediainfo_json
    res = Popen(command, stdin=stdin_parameter, stdout=PIPE, stderr=PIPE)
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\subprocess.py", line 971, in __init__
    self._execute_child(args, executable, preexec_fn, close_fds,
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\subprocess.py", line 1456, in _execute_child
    hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] 系统找不到指定的文件。



合成不了，是什么原因？大佬

无言***

财源滚滚 发表于 2025-3-22 00:40
Traceback (most recent call last):
  File "D:\FFT-f5\F5-TTS-V5\F5-TTS-V5\F5-TTS-V5\deepface\lib\site ...

文件路径不要那么长，直接放到磁盘根目录
https://deepface.cc/thread-152-1-1.html
这个也配置下

abc0***

谢谢楼主提供辛苦

pp5***

OSError: [WinError 126] 找不到指定的模块。 Error loading "D:\F5-TTS-V5\deepface\lib\site-packages\torch\lib\fbgemm.dll" or one of its dependencies.
请按任意键继续. . .

楼主这个是啥原因

无言***

pp5228 发表于 2025-3-25 22:54
OSError: [WinError 126] 找不到指定的模块。 Error loading "D:\F5-TTS-V5\deepface\lib\site-packages\to ...

新人必看里找

小***

补丁下了缺少文件也复制进去了，但是打开程序了合成以后显示错误

13070***

5080笔记本显卡  请问这个能解决吗  RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

无言***

13070208442 发表于 2025-4-8 11:56
5080笔记本显卡  请问这个能解决吗  RuntimeError: CUDA error: no kernel image is available for executi ...

不支持50系