whisper.json #177

New Issue

alxis · 2023-03-26T12:42:40Z

alxis commented

2023-03-26 12:42:40 +00:00

Hello dev first of all thanks alot for this awesome tool , i just started using it but when i try to create dataset i get this error

Loading specialized model for language: en
Loading Whisper model: base.en
Loaded Whisper model
Failed to transcribe: ./voices\zelda\vocal_000.wav
Failed to transcribe: ./voices\zelda\vocal_001.wav
Failed to transcribe: ./voices\zelda\vocal_002.wav
Failed to transcribe: ./voices\zelda\vocal_003.wav
Failed to transcribe: ./voices\zelda\vocal_004.wav
Failed to transcribe: ./voices\zelda\vocal_005.wav
Failed to transcribe: ./voices\zelda\vocal_006.wav
Failed to transcribe: ./voices\zelda\vocal_007.wav
Failed to transcribe: ./voices\zelda\vocal_008.wav
Traceback (most recent call last):
  File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict
    output = await app.get_blocks().process_api(
  File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api
    result = await self.call_function(
  File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 884, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "D:\ai\ai-audio-clone\ai-voice-cloning\src\webui.py", line 208, in prepare_dataset_proxy
    message = prepare_dataset( voice, use_segments=slice_audio, text_length=validation_text_length, audio_length=validation_audio_length, progress=progress )
  File "D:\ai\ai-audio-clone\ai-voice-cloning\src\utils.py", line 1570, in prepare_dataset
    raise Exception(f"Missing dataset: {infile}")
Exception: Missing dataset: ./training/zelda//whisper.json

Hello dev first of all thanks alot for this awesome tool , i just started using it but when i try to create dataset i get this error ``` Loading specialized model for language: en Loading Whisper model: base.en Loaded Whisper model Failed to transcribe: ./voices\zelda\vocal_000.wav Failed to transcribe: ./voices\zelda\vocal_001.wav Failed to transcribe: ./voices\zelda\vocal_002.wav Failed to transcribe: ./voices\zelda\vocal_003.wav Failed to transcribe: ./voices\zelda\vocal_004.wav Failed to transcribe: ./voices\zelda\vocal_005.wav Failed to transcribe: ./voices\zelda\vocal_006.wav Failed to transcribe: ./voices\zelda\vocal_007.wav Failed to transcribe: ./voices\zelda\vocal_008.wav Traceback (most recent call last): File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict output = await app.get_blocks().process_api( File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api result = await self.call_function( File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 884, in call_function prediction = await anyio.to_thread.run_sync( File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "D:\ai\ai-audio-clone\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run result = context.run(func, *args) File "D:\ai\ai-audio-clone\ai-voice-cloning\src\webui.py", line 208, in prepare_dataset_proxy message = prepare_dataset( voice, use_segments=slice_audio, text_length=validation_text_length, audio_length=validation_audio_length, progress=progress ) File "D:\ai\ai-audio-clone\ai-voice-cloning\src\utils.py", line 1570, in prepare_dataset raise Exception(f"Missing dataset: {infile}") Exception: Missing dataset: ./training/zelda//whisper.json ```

rasdasdw.png

96 KiB

psammites commented

2023-03-26 15:25:17 +00:00

Are those .wav files valid? You can use ffprobe to check.

Are those .wav files valid? You can use `ffprobe` to check.

alxis commented

2023-03-26 15:56:46 +00:00

they work fine in generating tab

alxis commented

2023-03-26 15:57:09 +00:00

Are those .wav files valid? You can use ffprobe to check.

how to do this

> Are those .wav files valid? You can use `ffprobe` to check. how to do this

psammites commented

2023-03-26 16:07:44 +00:00

how to do this

> how to do this ![](https://files.catbox.moe/w3ha7g.png)

❤️ 1

alxis commented

2023-03-26 18:19:06 +00:00

thanks it was that ffmpeg was not set in the path as environment variable ,everything is working now

for anyone with same issue just download ffmpeg-6.0 build and set it up as environment variable

thanks it was that ffmpeg was not set in the path as environment variable ,everything is working now for anyone with same issue just download ffmpeg-6.0 build and set it up as environment variable

alxis closed this issue

2023-03-26 18:19:27 +00:00

psammites referenced this issue

2023-03-26 20:54:22 +00:00

Would love a hand-holding tutorial on preparing a dataset... #178

pheonis referenced this issue

2023-05-01 07:56:19 +00:00

Trying to Transcribe but getting error: 'Missing dataset: ./training/voice1//whisper.json' #223

Sign in to join this conversation.