facebook

/

wav2vec2-lv-60-espeak-cv-ft

like 27

Follow

AI at Meta 3.87k

I got the exact same issue:

• transformers version: 4.46.2
• Platform: macOS-15.1-arm64-arm-64bit
• Python version: 3.12.7
• Huggingface_hub version: 0.26.2
• Safetensors version: 0.4.5
• Accelerate version: not installed
• Accelerate config: not found
• PyTorch version (GPU?): 2.5.1 (False)
• Tensorflow version (GPU?): not installed (NA)
• Flax version (CPU?/GPU?/TPU?): not installed (NA)
• Jax version: not installed
• JaxLib version: not installed
• Using distributed or parallel set-up in script?:

>>> from transformers import Wav2Vec2Processor
>>> processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-lv-60-espeak-cv-ft")
preprocessor_config.json: 100%|█████████████████████████████████████████| 212/212 [00:00<00:00, 351kB/s]
tokenizer_config.json: 100%|███████████████████████████████████████████| 321/321 [00:00<00:00, 4.01MB/s]
vocab.json: 100%|██████████████████████████████████████████████████| 4.64k/4.64k [00:00<00:00, 11.3MB/s]
special_tokens_map.json: 100%|████████████████████████████████████████| 85.0/85.0 [00:00<00:00, 475kB/s]
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File ".../venv/lib/python3.12/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py", line 59, in from_pretrained
    return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../venv/lib/python3.12/site-packages/transformers/processing_utils.py", line 947, in from_pretrained
    return cls.from_args_and_dict(args, processor_dict, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../venv/lib/python3.12/site-packages/transformers/processing_utils.py", line 745, in from_args_and_dict
    processor = cls(*args, **processor_dict)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../venv/lib/python3.12/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py", line 52, in __init__
    super().__init__(feature_extractor, tokenizer)
  File ".../venv/lib/python3.12/site-packages/transformers/processing_utils.py", line 387, in __init__
    raise TypeError(
TypeError: Received a bool for argument tokenizer, but a PreTrainedTokenizerBase was expected.```

Same issue here.

Python: 3.12.5
Transformers: 4.46.3
Torch: 2.5.1

Likewise