ochen1 / insanely-fast-whisper-cli Goto Github PK

报错
AssertionError: Torch not compiled with CUDA enabled

I installed it and got;

insanely-fast-whisper --model openai/whisper-base.en /Users/i/Desktop/Steve_Prince.wav
Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1353, in _get_module
return importlib.import_module("." + module_name, self.name)
File "/opt/anaconda3/lib/python3.9/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1030, in _gcd_import
File "", line 1007, in _find_and_load
File "", line 986, in _find_and_load_unlocked
File "", line 680, in _load_unlocked
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/opt/anaconda3/lib/python3.9/site-packages/transformers/pipelines/init.py", line 28, in
from ..image_processing_utils import BaseImageProcessor
File "/opt/anaconda3/lib/python3.9/site-packages/transformers/image_processing_utils.py", line 28, in
from .image_transforms import center_crop, normalize, rescale
File "/opt/anaconda3/lib/python3.9/site-packages/transformers/image_transforms.py", line 47, in
import tensorflow as tf
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/init.py", line 37, in
from tensorflow.python.tools import module_util as _module_util
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/python/init.py", line 37, in
from tensorflow.python.eager import context
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/python/eager/context.py", line 29, in
from tensorflow.core.framework import function_pb2
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/core/framework/function_pb2.py", line 16, in
from tensorflow.core.framework import attr_value_pb2 as tensorflow_dot_core_dot_framework_dot_attr__value__pb2
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/core/framework/attr_value_pb2.py", line 16, in
from tensorflow.core.framework import tensor_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__pb2
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/core/framework/tensor_pb2.py", line 16, in
from tensorflow.core.framework import resource_handle_pb2 as tensorflow_dot_core_dot_framework_dot_resource__handle__pb2
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/core/framework/resource_handle_pb2.py", line 16, in
from tensorflow.core.framework import tensor_shape_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2
File "/opt/anaconda3/lib/python3.9/site-packages/tensorflow/core/framework/tensor_shape_pb2.py", line 36, in
_descriptor.FieldDescriptor(
File "/opt/anaconda3/lib/python3.9/site-packages/google/protobuf/descriptor.py", line 553, in new
_message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:

1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/opt/anaconda3/bin/insanely-fast-whisper", line 5, in
from insanely_fast_whisper.cli import main
File "/opt/anaconda3/lib/python3.9/site-packages/insanely_fast_whisper/cli.py", line 4, in
from transformers import pipeline
File "", line 1055, in _handle_fromlist
File "/opt/anaconda3/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1343, in getattr
module = self._get_module(self._class_to_module[name])
File "/opt/anaconda3/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1355, in _get_module
raise RuntimeError(
RuntimeError: Failed to import transformers.pipelines because of the following error (look up to see its traceback):
Descriptors cannot be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:

1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates

When I run this command, i get an error message.

Command:
$ pip install -r requirements-gfx1010.txt --extra-index-url https://download.pytorch.org/whl/rocm5.2

Error:

Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/rocm5.2
Requirement already satisfied: click in c:\users\brodskithegreat\desktop\desktop\code\scraper-dl-vids\insanely-fast\venv\lib\site-packages (from -r requirements-gfx1010.txt (line 3)) (8.1.7)
Requirement already satisfied: transformers in c:\users\brodskithegreat\desktop\desktop\code\scraper-dl-vids\insanely-fast\venv\lib\site-packages (from -r requirements-gfx1010.txt (line 4)) (4.40.0.dev0)
ERROR: Could not find a version that satisfies the requirement torch==1.13.1+rocm5.2 (from versions: 1.11.0, 1.12.0, 1.12.1, 1.13.0, 1.13.1, 2.0.0, 2.0.1, 2.1.0, 2.1.1, 2.1.2, 2.2.0, 2.2.1, 2.2.2)
ERROR: No matching distribution found for torch==1.13.1+rocm5.2

I dont have a nvidia gpu and was hoping to play around with this AMD fix :/

I'm on a windows machine. Not sure if that matters, but this command doesnt work:

Command:
$ insanely-fast-whisper --model openai/whisper-base --device cpu --file-name myaudio.wav

Error:

C:\Users\BrodskiTheGreat\Desktop\desktop\Code\scraper-dl-vids\insanely-fast\venv\lib\site-packages\pyannote\audio\core\io.py:43: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
  torchaudio.set_audio_backend("soundfile")
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
  File "C:\Python310\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Python310\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\BrodskiTheGreat\Desktop\desktop\Code\scraper-dl-vids\insanely-fast\venv\Scripts\insanely-fast-whisper.exe\__main__.py", line 7, in <module>
  File "C:\Users\BrodskiTheGreat\Desktop\desktop\Code\scraper-dl-vids\insanely-fast\venv\lib\site-packages\insanely_fast_whisper\cli.py", line 94, in main
    pipe = pipeline(
  File "C:\Users\BrodskiTheGreat\Desktop\desktop\Code\scraper-dl-vids\insanely-fast\venv\lib\site-packages\transformers\pipelines\__init__.py", line 1108, in pipeline
    return pipeline_class(model=model, framework=framework, task=task, **kwargs)
  File "C:\Users\BrodskiTheGreat\Desktop\desktop\Code\scraper-dl-vids\insanely-fast\venv\lib\site-packages\transformers\pipelines\automatic_speech_recognition.py", line 220, in __init__
    super().__init__(model, tokenizer, feature_extractor, device=device, torch_dtype=torch_dtype, **kwargs)
  File "C:\Users\BrodskiTheGreat\Desktop\desktop\Code\scraper-dl-vids\insanely-fast\venv\lib\site-packages\transformers\pipelines\base.py", line 853, in __init__
    self.device = torch.device(device)
RuntimeError: Invalid device string: 'cuda:cpu'

Also when I run --device cuda:0 i get similar error
RuntimeError: Invalid device string: 'cuda:cuda:0'

I'm not familiar with transformers's pipeline, but looks like it's messing up some string concatenation

Hi @ochen1 , would this need a VAD for transcribing long audios, or does it have in built VAD capability? Thanks.

How can a user can pass language of audio as a parameter? output is in English whether the audio language is French or Spanish. How can we pass this argument to the process? Thanks