F5-TTS V4版 - 接入千问大语言模型，上海交大最新零样本语音克隆，文本转语音 本地一键整合包下载

ba***

感谢分享

用我***

感谢分享

xixixi***

微调模型还是不能用，转绿的时候，文件里面没有文字
To create a public link, set `share=True` in `launch()`.
E:\F5-TTS\F5-TTS-V4\python\lib\site-packages\transformers\models\whisper\generation_whisper.py:496: FutureWarning: The input name `inputs` is deprecated. Please make sure to use `input_features` instead.
  warnings.warn(
You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset

syp***

好奇，特别想试试这个工具好不好用

vip***

好像很强大的样子

te***

支持微调啊，我想试试

tdw***

有的整合包F5推理页面有加载模型按钮可以切换，这个不知道是没有还是我找不到。

wq0***

微调还是必不可少。  感谢大佬

tiany***

多谢多谢。

Fe***

To create a public link, set `share=True` in `launch()`.
Traceback (most recent call last):
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\gradio\queueing.py", line 536, in process_events
    response = await route_utils.call_process_api(
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\gradio\blocks.py", line 1935, in process_api
    result = await self.call_function(
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\gradio\blocks.py", line 1520, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\anyio\_backends\_asyncio.py", line 2441, in run_sync_in_worker_thread
    return await future
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\anyio\_backends\_asyncio.py", line 943, in run
    result = context.run(func, *args)
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\gradio\utils.py", line 826, in wrapper
    response = f(*args, **kwargs)
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\src\f5_tts\infer\infer_gradio.py", line 90, in infer
    ref_audio, ref_text = preprocess_ref_audio_text(ref_audio_orig, ref_text, show_info=show_info)
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\src\f5_tts\infer\utils_infer.py", line 227, in preprocess_ref_audio_text
    aseg = AudioSegment.from_file(ref_audio_orig)
  File "E:\project\AITTSASR\F5-TTS-V4\F5-TTS-V4\python\lib\site-packages\pydub\audio_segment.py", line 723, in from_file
    stdin_data = file.read()
AttributeError: 'NoneType' object has no attribute 'read'