Trying to train but I get "AttributeError: 'NoneType' object has no attribute 'transcribe'" #12

New Issue

AI_Pleb · 2023-02-20T01:33:45Z

AI_Pleb commented

2023-02-20 01:33:45 +00:00

I've been trying to prepare a small dataset for a character to train on (pictured), but I get an error with the following stack trace whenever I try:

Loaded TorToiSe, ready for generation.
Unloading TTS
Loading Whisper model: base
Transcribing file: ./voices\Bang_Shishigami\BNG_01_01_076.wav
Traceback (most recent call last):
  File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\routes.py", line 384, in run_predict
    output = await app.get_blocks().process_api(
  File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 1024, in process_api
    result = await self.call_function(
  File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 836, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "G:\Tortoise-TTS\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 "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\helpers.py", line 584, in tracked_fn
    response = fn(*args)
  File "G:\Tortoise-TTS\ai-voice-cloning\src\webui.py", line 181, in prepare_dataset_proxy
    return prepare_dataset( get_voices(load_latents=False)[voice], outdir=f"./training/{voice}/", language=language, progress=progress )
  File "G:\Tortoise-TTS\ai-voice-cloning\src\utils.py", line 481, in prepare_dataset
    result = whisper_model.transcribe(file, language=language if language else "English")
AttributeError: 'NoneType' object has no attribute 'transcribe'

I've been trying to prepare a small dataset for a character to train on (pictured), but I get an error with the following stack trace whenever I try: ``` Loaded TorToiSe, ready for generation. Unloading TTS Loading Whisper model: base Transcribing file: ./voices\Bang_Shishigami\BNG_01_01_076.wav Traceback (most recent call last): File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\routes.py", line 384, in run_predict output = await app.get_blocks().process_api( File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 1024, in process_api result = await self.call_function( File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\blocks.py", line 836, in call_function prediction = await anyio.to_thread.run_sync( File "G:\Tortoise-TTS\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 "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run result = context.run(func, *args) File "G:\Tortoise-TTS\ai-voice-cloning\venv\lib\site-packages\gradio\helpers.py", line 584, in tracked_fn response = fn(*args) File "G:\Tortoise-TTS\ai-voice-cloning\src\webui.py", line 181, in prepare_dataset_proxy return prepare_dataset( get_voices(load_latents=False)[voice], outdir=f"./training/{voice}/", language=language, progress=progress ) File "G:\Tortoise-TTS\ai-voice-cloning\src\utils.py", line 481, in prepare_dataset result = whisper_model.transcribe(file, language=language if language else "English") AttributeError: 'NoneType' object has no attribute 'transcribe' ```

5e1c68ecfd763484cb8be5bf7006b510.png

100 KiB

fde09f204c9ce62ee07f8e351b3189c9.png

65 KiB