openai

/

whisper-large-v3

like 2.61k

Here is my modified code specifying the local path of whisper files:

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "E:\LLM\whisper-large-v3\models"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)


result = pipe("audio.mp3",return_timestamps=True)
print(result["text"])

And it shows:

raceback (most recent call last):
  File "e:\LLM\whisper-large-v3\main.py", line 15, in <module>
    processor = AutoProcessor.from_pretrained(model_id)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\LLM\chatglm2-6b\.venv\Lib\site-packages\transformers\models\auto\processing_auto.py", line 268, in from_pretrained
    return processor_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\LLM\chatglm2-6b\.venv\Lib\site-packages\transformers\processing_utils.py", line 184, in from_pretrained
    args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\LLM\chatglm2-6b\.venv\Lib\site-packages\transformers\processing_utils.py", line 228, in _get_arguments_from_pretrained
    args.append(attribute_class.from_pretrained(pretrained_model_name_or_path, **kwargs))
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\LLM\chatglm2-6b\.venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 1825, in from_pretrained
    return cls._from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^
  File "E:\LLM\chatglm2-6b\.venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 1988, in _from_pretrained
    tokenizer = cls(*init_inputs, **init_kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\LLM\chatglm2-6b\.venv\Lib\site-packages\transformers\models\whisper\tokenization_whisper.py", line 293, in __init__
    with open(merges_file, encoding="utf-8") as merges_handle:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: expected str, bytes or os.PathLike object, not NoneType

How to fix that?