whisperX doesn't work but faster-whisper does #77

Snuupy · 2023-10-27T01:55:23Z

Snuupy
Oct 27, 2023

Hi, I'm running into a ctranslate2 error and I don't know why. faster-whisper works but whisperX doesn't.

Here are the logs:

(subsai) root@snuminipc:~/subsai# time subsai "/mnt/a/1.mp4" --model m-bain/whisperX --format srt
[01:47:17] INFO     Created a temporary directory at /tmp/tmpi8zf7lfk                                   instantiator.py:21
           INFO     Writing /tmp/tmpi8zf7lfk/_remote_module_non_scriptable.py                           instantiator.py:76
           WARNING  torchvision is not available - cannot save figures                                 train_logger.py:227

███████╗██╗   ██╗██████╗ ███████╗     █████╗ ██╗
██╔════╝██║   ██║██╔══██╗██╔════╝    ██╔══██╗██║
███████╗██║   ██║██████╔╝███████╗    ███████║██║
╚════██║██║   ██║██╔══██╗╚════██║    ██╔══██║██║
███████║╚██████╔╝██████╔╝███████║    ██║  ██║██║
╚══════╝ ╚═════╝ ╚═════╝ ╚══════╝    ╚═╝  ╚═╝╚═╝
                                            
Subs AI: Subtitles generation tool powered by OpenAI's Whisper and its variants.
Version: 1.2.1               
===================================

[-] Model name: m-bain/whisperX
[-] Model configs: defaults
---
[+] Initializing the model
Traceback (most recent call last):
  File "/root/subsai/bin/subsai", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/root/subsai/lib/python3.11/site-packages/subsai/cli.py", line 149, in main
    run(media_file_arg=args.media_file,
  File "/root/subsai/lib/python3.11/site-packages/subsai/cli.py", line 81, in run
    model = subs_ai.create_model(model_name, model_configs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai/lib/python3.11/site-packages/subsai/main.py", line 96, in create_model
    return AVAILABLE_MODELS[model_name]['class'](model_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai/lib/python3.11/site-packages/subsai/models/whisperX_model.py", line 123, in __init__
    self.model = whisperx.load_model(self.model_type,
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai/lib/python3.11/site-packages/whisperx/asr.py", line 50, in load_model
    model = WhisperModel(whisper_arch,
            ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai/lib/python3.11/site-packages/faster_whisper/transcribe.py", line 120, in __init__
    self.model = ctranslate2.models.Whisper(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: __init__(): incompatible constructor arguments. The following argument types are supported:
    1. ctranslate2._ext.Whisper(model_path: str, device: str = 'cpu', *, device_index: Union[int, List[int]] = 0, compute_type: Union[str, Dict[str, str]] = 'default', inter_threads: int = 1, intra_threads: int = 0, max_queued_batches: int = 0, files: object = None)

Invoked with: '/root/.cache/huggingface/hub/models--guillaumekln--faster-whisper-base/snapshots/515102184abb526d1cfb9c882107192588d7250a'; kwargs: device=None, device_index=0, compute_type='default', intra_threads=0, inter_threads=1

real    0m6.253s
user    0m5.464s
sys     0m1.358s

Any ideas?

If it matters, CPU is an Intel N5095 (yes, very underpowered) which does not support AVX, but does support SSE4.2, which should mean ctranslate2 should be supported as per https://opennmt.net/CTranslate2/hardware_support.html which says it only requires at least SSE4.1. Also strange is why faster-whisper works but whisperX doesn't?

# cat /proc/cpuinfo
model name      : Intel(R) Celeron(R) N5095 @ 2.00GHz

Appreciate the help/ideas in advance. Thanks.

Answered by absadiki

Oct 29, 2023

Sorry @Snuupy, I was mistaken, I am the one who get crazy now lol

As I though, I did set all the models to take the base model by default, so you can use the model without specifying the model type.

After debugging, I found that I was setting the device to None as a default value, but faster-whisper requires a str.

Please pull the latest commit and give it a try now ?

View full answer

absadiki · 2023-10-28T00:01:49Z

absadiki
Oct 28, 2023
Maintainer

Hi @Snuupy ,

Yes your CPU is supported, and indeed faster-whisper is working as you said, so this is a bug in WhisperX I believe.
Could you please verify which version of WhisperX are you using, because the latest version is not stable when I did some tests recently.
Please make sure you are using the same commit I am using here and I suggest to install subsai in a separate virtual environment.
You can try with Docker as well and see if it works.

6 replies

Snuupy Oct 28, 2023
Author

Hi, thank you for the reply.

this is a bug in WhisperX

OK great, glad to confirm I'm not crazy lol

verify which version of WhisperX are you using

pip list shows whisperx 3.1.1 but does not give me commit hash. I used the pip install git+https://github.com/abdeladim-s/subsai command on the main page and I also tried the docker container as well.

For the sake of debugging I did pip uninstall whisperx and then pip install git+https://github.com/m-bain/whisperx@0ae0d49d1dd789322181f579c71719f4cac83ae1

install subsai in a separate virtual environment.

it already is, as denoted by (subsai) before the terminal

You can try with Docker as well and see if it works.

I did try this as well but did not attach logs, same issue.

I tried with a fresh new venv, and ran into the same error:

root@snuminipc:~# python3 -m venv subsai2
root@snuminipc:~# source subsai2/bin/activate
(subsai2) root@snuminipc:~# ffmpeg
ffmpeg version 5.1.2-3ubuntu1 Copyright (c) 2000-2022 the FFmpeg developers
(subsai2) root@snuminipc:~# cd subsai2
(subsai2) root@snuminipc:~/subsai2# ls
bin  include  lib  lib64  pyvenv.cfg
(subsai2) root@snuminipc:~/subsai2# pip install setuptools-rust
Collecting setuptools-rust
  Downloading setuptools_rust-1.8.0-py3-none-any.whl (26 kB)
Requirement already satisfied: setuptools>=62.4 in ./lib/python3.11/site-packages (from setuptools-rust) (66.1.1)
Collecting semantic-version<3,>=2.8.2
  Using cached semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)
Installing collected packages: semantic-version, setuptools-rust
Successfully installed semantic-version-2.10.0 setuptools-rust-1.8.0
(subsai2) root@snuminipc:~/subsai2# pip install git+https://github.com/abdeladim-s/subsai
Collecting git+https://github.com/abdeladim-s/subsai
  Cloning https://github.com/abdeladim-s/subsai to /tmp/pip-req-build-mc7935br
  Running command git clone --filter=blob:none --quiet https://github.com/abdeladim-s/subsai /tmp/pip-req-build-mc7935br
  Resolved https://github.com/abdeladim-s/subsai to commit b77f10637d5b967dca366e44493dc872206a7379
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Installing backend dependencies ... done
  Preparing metadata (pyproject.toml) ... done
Collecting whisper-timestamped@ git+https://github.com/linto-ai/whisper-timestamped
  Cloning https://github.com/linto-ai/whisper-timestamped to /tmp/pip-install-86eh1ul0/whisper-timestamped_95199940cee84e1f95f8689b1385e454
  Running command git clone --filter=blob:none --quiet https://github.com/linto-ai/whisper-timestamped /tmp/pip-install-86eh1ul0/whisper-timestamped_95199940cee84e1f95f8689b1385e454
  Resolved https://github.com/linto-ai/whisper-timestamped to commit 127e8b738756420487210490d09938593244b3dd
  Preparing metadata (setup.py) ... done
Collecting whisperx@ git+https://github.com/m-bain/whisperx@0ae0d49d1dd789322181f579c71719f4cac83ae1
  Using cached whisperx-3.1.1-py3-none-any.whl
Collecting torch==2.0.1
  Using cached torch-2.0.1-cp311-cp311-manylinux1_x86_64.whl (619.9 MB)
Collecting openai-whisper==20230124
  Using cached openai_whisper-20230124-py3-none-any.whl
Collecting streamlit~=1.20.0
  Using cached streamlit-1.20.0-py2.py3-none-any.whl (9.6 MB)
Collecting streamlit-player~=0.1.5
  Using cached streamlit_player-0.1.5-py3-none-any.whl (1.7 MB)
Collecting streamlit-aggrid~=0.3.4
  Using cached streamlit_aggrid-0.3.4.post3-py3-none-any.whl (3.4 MB)
Collecting ffsubsync~=0.4.24
  Using cached ffsubsync-0.4.25-py2.py3-none-any.whl (36 kB)
Collecting pandas==1.5.3
  Using cached pandas-1.5.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.0 MB)
Collecting pysubs2~=1.6.0
  Using cached pysubs2-1.6.1-py3-none-any.whl (35 kB)
Collecting pywhispercpp==1.1.1
  Using cached pywhispercpp-1.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (634 kB)
Collecting dl-translate==0.2.6
  Using cached dl_translate-0.2.6-py3-none-any.whl (14 kB)
Collecting faster-whisper==0.5.1
  Using cached faster_whisper-0.5.1-py3-none-any.whl (1.5 MB)
Collecting transformers>=4.4.0
  Downloading transformers-4.34.1-py3-none-any.whl (7.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.7/7.7 MB 54.7 MB/s eta 0:00:00
Collecting sentencepiece
  Using cached sentencepiece-0.1.99-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
Collecting protobuf
  Downloading protobuf-4.24.4-cp37-abi3-manylinux2014_x86_64.whl (311 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 311.6/311.6 kB 16.7 MB/s eta 0:00:00
Collecting tqdm
  Downloading tqdm-4.66.1-py3-none-any.whl (78 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 78.3/78.3 kB 15.2 MB/s eta 0:00:00
Collecting av==10.*
  Using cached av-10.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (31.2 MB)
Collecting ctranslate2<4,>=3.10
  Downloading ctranslate2-3.20.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (35.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 35.9/35.9 MB 7.1 MB/s eta 0:00:00
Collecting huggingface-hub>=0.13
  Downloading huggingface_hub-0.18.0-py3-none-any.whl (301 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 302.0/302.0 kB 56.1 MB/s eta 0:00:00
Collecting tokenizers==0.13.*
  Using cached tokenizers-0.13.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)
Collecting ffmpeg-python==0.2.0
  Using cached ffmpeg_python-0.2.0-py3-none-any.whl (25 kB)
Collecting more-itertools
  Downloading more_itertools-10.1.0-py3-none-any.whl (55 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 55.8/55.8 kB 15.6 MB/s eta 0:00:00
Collecting numpy
  Downloading numpy-1.26.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 18.2/18.2 MB 12.9 MB/s eta 0:00:00
Collecting python-dateutil>=2.8.1
  Using cached python_dateutil-2.8.2-py2.py3-none-any.whl (247 kB)
Collecting pytz>=2020.1
  Downloading pytz-2023.3.post1-py2.py3-none-any.whl (502 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 502.5/502.5 kB 43.7 MB/s eta 0:00:00
Collecting pydub
  Using cached pydub-0.25.1-py2.py3-none-any.whl (32 kB)
Collecting requests
  Using cached requests-2.31.0-py3-none-any.whl (62 kB)
Collecting platformdirs
  Downloading platformdirs-3.11.0-py3-none-any.whl (17 kB)
Collecting filelock
  Downloading filelock-3.13.0-py3-none-any.whl (11 kB)
Collecting typing-extensions
  Using cached typing_extensions-4.8.0-py3-none-any.whl (31 kB)
Collecting sympy
  Using cached sympy-1.12-py3-none-any.whl (5.7 MB)
Collecting networkx
  Downloading networkx-3.2-py3-none-any.whl (1.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 75.3 MB/s eta 0:00:00
Collecting jinja2
  Using cached Jinja2-3.1.2-py3-none-any.whl (133 kB)
Collecting nvidia-cuda-nvrtc-cu11==11.7.99
  Using cached nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl (21.0 MB)
Collecting nvidia-cuda-runtime-cu11==11.7.99
  Using cached nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl (849 kB)
Collecting nvidia-cuda-cupti-cu11==11.7.101
  Using cached nvidia_cuda_cupti_cu11-11.7.101-py3-none-manylinux1_x86_64.whl (11.8 MB)
Collecting nvidia-cudnn-cu11==8.5.0.96
  Using cached nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl (557.1 MB)
Collecting nvidia-cublas-cu11==11.10.3.66
  Using cached nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl (317.1 MB)
Collecting nvidia-cufft-cu11==10.9.0.58
  Using cached nvidia_cufft_cu11-10.9.0.58-py3-none-manylinux1_x86_64.whl (168.4 MB)
Collecting nvidia-curand-cu11==10.2.10.91
  Using cached nvidia_curand_cu11-10.2.10.91-py3-none-manylinux1_x86_64.whl (54.6 MB)
Collecting nvidia-cusolver-cu11==11.4.0.1
  Using cached nvidia_cusolver_cu11-11.4.0.1-2-py3-none-manylinux1_x86_64.whl (102.6 MB)
Collecting nvidia-cusparse-cu11==11.7.4.91
  Using cached nvidia_cusparse_cu11-11.7.4.91-py3-none-manylinux1_x86_64.whl (173.2 MB)
Collecting nvidia-nccl-cu11==2.14.3
  Using cached nvidia_nccl_cu11-2.14.3-py3-none-manylinux1_x86_64.whl (177.1 MB)
Collecting nvidia-nvtx-cu11==11.7.91
  Using cached nvidia_nvtx_cu11-11.7.91-py3-none-manylinux1_x86_64.whl (98 kB)
Collecting triton==2.0.0
  Using cached triton-2.0.0-1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (63.3 MB)
Collecting future
  Using cached future-0.18.3-py3-none-any.whl
Requirement already satisfied: setuptools in ./lib/python3.11/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch==2.0.1->subsai==1.2.1) (66.1.1)
Collecting wheel
  Using cached wheel-0.41.2-py3-none-any.whl (64 kB)
Collecting cmake
  Downloading cmake-3.27.7-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (26.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 26.0/26.0 MB 11.6 MB/s eta 0:00:00
Collecting lit
  Downloading lit-17.0.3.tar.gz (154 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 154.7/154.7 kB 15.4 MB/s eta 0:00:00
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Installing backend dependencies ... done
  Preparing metadata (pyproject.toml) ... done
Collecting auditok==0.1.5
  Using cached auditok-0.1.5-py3-none-any.whl
Collecting charset-normalizer
  Downloading charset_normalizer-3.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (137 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 137.5/137.5 kB 21.5 MB/s eta 0:00:00
Collecting faust-cchardet
  Downloading faust_cchardet-2.1.19-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (313 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 313.2/313.2 kB 19.6 MB/s eta 0:00:00
Collecting rich
  Downloading rich-13.6.0-py3-none-any.whl (239 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 239.8/239.8 kB 19.4 MB/s eta 0:00:00
Collecting six
  Using cached six-1.16.0-py2.py3-none-any.whl (11 kB)
Collecting srt>=3.0.0
  Using cached srt-3.5.3-py3-none-any.whl
Collecting webrtcvad
  Using cached webrtcvad-2.0.10-cp311-cp311-linux_x86_64.whl
Collecting chardet
  Downloading chardet-5.2.0-py3-none-any.whl (199 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 199.4/199.4 kB 28.3 MB/s eta 0:00:00
Collecting altair<5,>=3.2.0
  Using cached altair-4.2.2-py3-none-any.whl (813 kB)
Collecting blinker>=1.0.0
  Downloading blinker-1.6.3-py3-none-any.whl (13 kB)
Collecting cachetools>=4.0
  Downloading cachetools-5.3.2-py3-none-any.whl (9.3 kB)
Collecting click>=7.0
  Downloading click-8.1.7-py3-none-any.whl (97 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 97.9/97.9 kB 1.7 MB/s eta 0:00:00
Collecting importlib-metadata>=1.4
  Using cached importlib_metadata-6.8.0-py3-none-any.whl (22 kB)
Collecting packaging>=14.1
  Using cached packaging-23.2-py3-none-any.whl (53 kB)
Collecting pillow>=6.2.0
  Downloading Pillow-10.1.0-cp311-cp311-manylinux_2_28_x86_64.whl (3.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.6/3.6 MB 23.1 MB/s eta 0:00:00
Collecting protobuf
  Using cached protobuf-3.20.3-py2.py3-none-any.whl (162 kB)
Collecting pyarrow>=4.0
  Downloading pyarrow-13.0.0-cp311-cp311-manylinux_2_28_x86_64.whl (40.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 40.0/40.0 MB 11.7 MB/s eta 0:00:00
Collecting pympler>=0.9
  Using cached Pympler-1.0.1-py3-none-any.whl (164 kB)
Collecting semver
  Downloading semver-3.0.2-py3-none-any.whl (17 kB)
Collecting toml
  Using cached toml-0.10.2-py2.py3-none-any.whl (16 kB)
Collecting tzlocal>=1.1
  Downloading tzlocal-5.2-py3-none-any.whl (17 kB)
Collecting validators>=0.2
  Downloading validators-0.22.0-py3-none-any.whl (26 kB)
Collecting gitpython!=3.1.19
  Downloading GitPython-3.1.40-py3-none-any.whl (190 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 190.6/190.6 kB 15.4 MB/s eta 0:00:00
Collecting pydeck>=0.1.dev5
  Using cached pydeck-0.8.1b0-py2.py3-none-any.whl (4.8 MB)
Collecting tornado>=6.0.3
  Downloading tornado-6.3.3-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (427 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 427.7/427.7 kB 11.8 MB/s eta 0:00:00
Collecting watchdog
  Using cached watchdog-3.0.0-py3-none-manylinux2014_x86_64.whl (82 kB)
Collecting python-decouple<4.0,>=3.6
  Using cached python_decouple-3.8-py3-none-any.whl (9.9 kB)
Collecting Cython
  Downloading Cython-3.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.6/3.6 MB 11.4 MB/s eta 0:00:00
Collecting dtw-python
  Using cached dtw_python-1.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (666 kB)
Collecting pyannote.audio@ git+https://github.com/pyannote/pyannote-audio@11b56a137a578db9335efc00298f6ec1932e6317
  Using cached pyannote.audio-2.1.1-py2.py3-none-any.whl
Collecting nltk
  Using cached nltk-3.8.1-py3-none-any.whl (1.5 MB)
Collecting torchaudio>=2
  Downloading torchaudio-2.1.0-cp311-cp311-manylinux1_x86_64.whl (3.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.3/3.3 MB 12.0 MB/s eta 0:00:00
Collecting entrypoints
  Using cached entrypoints-0.4-py3-none-any.whl (5.3 kB)
Collecting jsonschema>=3.0
  Downloading jsonschema-4.19.1-py3-none-any.whl (83 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 83.3/83.3 kB 19.5 MB/s eta 0:00:00
Collecting toolz
  Using cached toolz-0.12.0-py3-none-any.whl (55 kB)
Collecting pyyaml<7,>=5.3
  Downloading PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (757 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 757.7/757.7 kB 44.0 MB/s eta 0:00:00
Collecting gitdb<5,>=4.0.1
  Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.7/62.7 kB 13.9 MB/s eta 0:00:00
Collecting fsspec>=2023.5.0
  Downloading fsspec-2023.10.0-py3-none-any.whl (166 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 166.4/166.4 kB 39.0 MB/s eta 0:00:00
Collecting zipp>=0.5
  Downloading zipp-3.17.0-py3-none-any.whl (7.4 kB)
Collecting MarkupSafe>=2.0
  Using cached MarkupSafe-2.1.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (28 kB)
Collecting idna<4,>=2.5
  Using cached idna-3.4-py3-none-any.whl (61 kB)
Collecting urllib3<3,>=1.21.1
  Downloading urllib3-2.0.7-py3-none-any.whl (124 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 124.2/124.2 kB 26.6 MB/s eta 0:00:00
Collecting certifi>=2017.4.17
  Downloading certifi-2023.7.22-py3-none-any.whl (158 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 158.3/158.3 kB 38.4 MB/s eta 0:00:00
Collecting markdown-it-py>=2.2.0
  Using cached markdown_it_py-3.0.0-py3-none-any.whl (87 kB)
Collecting pygments<3.0.0,>=2.13.0
  Downloading Pygments-2.16.1-py3-none-any.whl (1.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 37.6 MB/s eta 0:00:00
Collecting torchaudio>=2
  Using cached torchaudio-2.0.2-cp311-cp311-manylinux1_x86_64.whl (4.4 MB)
Collecting regex!=2019.12.17
  Downloading regex-2023.10.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (785 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 785.1/785.1 kB 25.6 MB/s eta 0:00:00
Collecting transformers>=4.4.0
  Downloading transformers-4.34.0-py3-none-any.whl (7.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.7/7.7 MB 25.0 MB/s eta 0:00:00
  Downloading transformers-4.33.3-py3-none-any.whl (7.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.6/7.6 MB 12.5 MB/s eta 0:00:00
Collecting safetensors>=0.3.1
  Downloading safetensors-0.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 16.7 MB/s eta 0:00:00
Collecting scipy>=1.1
  Downloading scipy-1.11.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (36.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 36.4/36.4 MB 30.7 MB/s eta 0:00:00
Collecting joblib
  Downloading joblib-1.3.2-py3-none-any.whl (302 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 302.2/302.2 kB 27.8 MB/s eta 0:00:00
Collecting asteroid-filterbanks>=0.4
  Using cached asteroid_filterbanks-0.4.0-py3-none-any.whl (29 kB)
Collecting einops>=0.6.0
  Downloading einops-0.7.0-py3-none-any.whl (44 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 44.6/44.6 kB 12.0 MB/s eta 0:00:00
Collecting lightning>=2.0.1
  Downloading lightning-2.1.0-py3-none-any.whl (2.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.0/2.0 MB 22.9 MB/s eta 0:00:00
Collecting omegaconf<3.0,>=2.1
  Using cached omegaconf-2.3.0-py3-none-any.whl (79 kB)
Collecting pyannote.core>=5.0.0
  Using cached pyannote.core-5.0.0-py3-none-any.whl (58 kB)
Collecting pyannote.database>=5.0.1
  Using cached pyannote.database-5.0.1-py3-none-any.whl (48 kB)
Collecting pyannote.metrics>=3.2
  Using cached pyannote.metrics-3.2.1-py3-none-any.whl (51 kB)
Collecting pyannote.pipeline>=2.3
  Downloading pyannote.pipeline-3.0.1-py3-none-any.whl (31 kB)
Collecting pytorch-metric-learning>=2.1.0
  Using cached pytorch_metric_learning-2.3.0-py3-none-any.whl (115 kB)
Collecting soundfile>=0.12.1
  Using cached soundfile-0.12.1-py2.py3-none-manylinux_2_31_x86_64.whl (1.2 MB)
Collecting speechbrain>=0.5.14
  Using cached speechbrain-0.5.15-py3-none-any.whl (553 kB)
Collecting tensorboardX>=2.6
  Downloading tensorboardX-2.6.2.2-py2.py3-none-any.whl (101 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 101.7/101.7 kB 18.9 MB/s eta 0:00:00
Collecting torch-audiomentations>=0.11.0
  Using cached torch_audiomentations-0.11.0-py3-none-any.whl (47 kB)
Collecting torchmetrics>=0.11.0
  Downloading torchmetrics-1.2.0-py3-none-any.whl (805 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 805.2/805.2 kB 25.3 MB/s eta 0:00:00
Collecting mpmath>=0.19
  Using cached mpmath-1.3.0-py3-none-any.whl (536 kB)
Collecting smmap<6,>=3.0.1
  Downloading smmap-5.0.1-py3-none-any.whl (24 kB)
Collecting attrs>=22.2.0
  Using cached attrs-23.1.0-py3-none-any.whl (61 kB)
Collecting jsonschema-specifications>=2023.03.6
  Downloading jsonschema_specifications-2023.7.1-py3-none-any.whl (17 kB)
Collecting referencing>=0.28.4
  Downloading referencing-0.30.2-py3-none-any.whl (25 kB)
Collecting rpds-py>=0.7.1
  Downloading rpds_py-0.10.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 10.3 MB/s eta 0:00:00
Collecting lightning-utilities<2.0,>=0.8.0
  Using cached lightning_utilities-0.9.0-py3-none-any.whl (23 kB)
Collecting pytorch-lightning
  Downloading pytorch_lightning-2.1.0-py3-none-any.whl (774 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 774.6/774.6 kB 5.3 MB/s eta 0:00:00
Collecting mdurl~=0.1
  Using cached mdurl-0.1.2-py3-none-any.whl (10.0 kB)
Collecting antlr4-python3-runtime==4.9.*
  Using cached antlr4_python3_runtime-4.9.3-py3-none-any.whl
Collecting sortedcontainers>=2.0.4
  Using cached sortedcontainers-2.4.0-py2.py3-none-any.whl (29 kB)
Collecting typer[all]>=0.2.1
  Using cached typer-0.9.0-py3-none-any.whl (45 kB)
Collecting scikit-learn>=0.17.1
  Downloading scikit_learn-1.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 10.9/10.9 MB 28.0 MB/s eta 0:00:00
Collecting docopt>=0.6.2
  Using cached docopt-0.6.2-py2.py3-none-any.whl
Collecting tabulate>=0.7.7
  Using cached tabulate-0.9.0-py3-none-any.whl (35 kB)
Collecting matplotlib>=2.0.0
  Downloading matplotlib-3.8.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.6/11.6 MB 24.8 MB/s eta 0:00:00
Collecting optuna>=3.1
  Downloading optuna-3.4.0-py3-none-any.whl (409 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 409.6/409.6 kB 43.5 MB/s eta 0:00:00
Collecting cffi>=1.0
  Downloading cffi-1.16.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (464 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 464.8/464.8 kB 52.5 MB/s eta 0:00:00
Collecting hyperpyyaml
  Downloading HyperPyYAML-1.2.2-py3-none-any.whl (16 kB)
Collecting julius<0.3,>=0.2.3
  Using cached julius-0.2.7-py3-none-any.whl
Collecting librosa>=0.6.0
  Downloading librosa-0.10.1-py3-none-any.whl (253 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 253.7/253.7 kB 32.1 MB/s eta 0:00:00
Collecting torch-pitch-shift>=1.2.2
  Using cached torch_pitch_shift-1.2.4-py3-none-any.whl (4.9 kB)
Collecting pycparser
  Using cached pycparser-2.21-py2.py3-none-any.whl (118 kB)
Collecting aiohttp!=4.0.0a0,!=4.0.0a1
  Downloading aiohttp-3.8.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 MB 46.8 MB/s eta 0:00:00
Collecting audioread>=2.1.9
  Downloading audioread-3.0.1-py3-none-any.whl (23 kB)
Collecting decorator>=4.3.0
  Using cached decorator-5.1.1-py3-none-any.whl (9.1 kB)
Collecting numba>=0.51.0
  Downloading numba-0.58.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (3.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.6/3.6 MB 48.6 MB/s eta 0:00:00
Collecting pooch>=1.0
  Downloading pooch-1.8.0-py3-none-any.whl (62 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.7/62.7 kB 20.2 MB/s eta 0:00:00
Collecting soxr>=0.3.2
  Downloading soxr-0.3.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 53.7 MB/s eta 0:00:00
Collecting lazy-loader>=0.1
  Using cached lazy_loader-0.3-py3-none-any.whl (9.1 kB)
Collecting msgpack>=1.0
  Downloading msgpack-1.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (557 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 558.0/558.0 kB 68.4 MB/s eta 0:00:00
Collecting contourpy>=1.0.1
  Downloading contourpy-1.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (302 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 302.8/302.8 kB 5.1 MB/s eta 0:00:00
Collecting cycler>=0.10
  Downloading cycler-0.12.1-py3-none-any.whl (8.3 kB)
Collecting fonttools>=4.22.0
  Downloading fonttools-4.43.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.8/4.8 MB 31.8 MB/s eta 0:00:00
Collecting kiwisolver>=1.0.1
  Downloading kiwisolver-1.4.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.4/1.4 MB 61.1 MB/s eta 0:00:00
Collecting pyparsing>=2.3.1
  Downloading pyparsing-3.1.1-py3-none-any.whl (103 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 103.1/103.1 kB 29.5 MB/s eta 0:00:00
Collecting alembic>=1.5.0
  Downloading alembic-1.12.1-py3-none-any.whl (226 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 226.8/226.8 kB 48.0 MB/s eta 0:00:00
Collecting colorlog
  Using cached colorlog-6.7.0-py2.py3-none-any.whl (11 kB)
Collecting sqlalchemy>=1.3.0
  Downloading SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.2/3.2 MB 12.6 MB/s eta 0:00:00
Collecting threadpoolctl>=2.0.0
  Using cached threadpoolctl-3.2.0-py3-none-any.whl (15 kB)
Collecting primePy>=1.3
  Using cached primePy-1.3-py3-none-any.whl (4.0 kB)
Collecting colorama<0.5.0,>=0.4.3
  Using cached colorama-0.4.6-py2.py3-none-any.whl (25 kB)
Collecting shellingham<2.0.0,>=1.3.0
  Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)
Collecting ruamel.yaml>=0.17.28
  Downloading ruamel.yaml-0.18.2-py3-none-any.whl (113 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 113.7/113.7 kB 30.5 MB/s eta 0:00:00
Collecting multidict<7.0,>=4.5
  Using cached multidict-6.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (117 kB)
Collecting async-timeout<5.0,>=4.0.0a3
  Downloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB)
Collecting yarl<2.0,>=1.0
  Using cached yarl-1.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (282 kB)
Collecting frozenlist>=1.1.1
  Using cached frozenlist-1.4.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (250 kB)
Collecting aiosignal>=1.1.2
  Using cached aiosignal-1.3.1-py3-none-any.whl (7.6 kB)
Collecting Mako
  Using cached Mako-1.2.4-py3-none-any.whl (78 kB)
Collecting llvmlite<0.42,>=0.41.0dev0
  Downloading llvmlite-0.41.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (43.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 43.6/43.6 MB 24.8 MB/s eta 0:00:00
Collecting ruamel.yaml.clib>=0.2.7
  Downloading ruamel.yaml.clib-0.2.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (544 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 544.0/544.0 kB 50.4 MB/s eta 0:00:00
Collecting greenlet!=0.4.17
  Downloading greenlet-3.0.1-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (616 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 616.7/616.7 kB 9.2 MB/s eta 0:00:00
Building wheels for collected packages: subsai, lit
  Building wheel for subsai (pyproject.toml) ... done
  Created wheel for subsai: filename=subsai-1.2.1-py3-none-any.whl size=46845 sha256=69caff92e5bddb65baf0e55f4d6959afa144be1c8b736a79a244ec1b406c0c67
  Stored in directory: /tmp/pip-ephem-wheel-cache-zstzkwt8/wheels/84/90/8f/ef1c005513ea5d8f0aeff169382c368d73d720e99063761651
  Building wheel for lit (pyproject.toml) ... done
  Created wheel for lit: filename=lit-17.0.3-py3-none-any.whl size=93257 sha256=ba1041507e51b75c3d50b2665dd966fa7d6635573bd602fe6702ec30eb343bfa
  Stored in directory: /root/.cache/pip/wheels/72/5e/64/56728959b0b869406a7aa60a7e41cf5f79161fc7b8b54357ff
Successfully built subsai lit
Installing collected packages: webrtcvad, tokenizers, sortedcontainers, sentencepiece, pytz, python-decouple, pydub, primePy, mpmath, lit, faust-cchardet, docopt, cmake, av, auditok, antlr4-python3-runtime, zipp, wheel, watchdog, validators, urllib3, tzlocal, typing-extensions, tqdm, tornado, toolz, toml, threadpoolctl, tabulate, sympy, srt, smmap, six, shellingham, semver, safetensors, ruamel.yaml.clib, rpds-py, regex, pyyaml, pysubs2, pyparsing, pympler, pygments, pycparser, protobuf, platformdirs, pillow, packaging, nvidia-nccl-cu11, nvidia-cufft-cu11, nvidia-cuda-nvrtc-cu11, numpy, networkx, multidict, msgpack, more-itertools, mdurl, MarkupSafe, llvmlite, lazy-loader, kiwisolver, joblib, idna, greenlet, future, fsspec, frozenlist, fonttools, filelock, entrypoints, einops, decorator, Cython, cycler, colorlog, colorama, click, charset-normalizer, chardet, certifi, cachetools, blinker, audioread, attrs, async-timeout, yarl, typer, tensorboardX, sqlalchemy, soxr, scipy, ruamel.yaml, requests, referencing, python-dateutil, pyarrow, omegaconf, nvidia-nvtx-cu11, nvidia-cusparse-cu11, nvidia-curand-cu11, nvidia-cuda-runtime-cu11, nvidia-cuda-cupti-cu11, nvidia-cublas-cu11, numba, nltk, markdown-it-py, Mako, lightning-utilities, jinja2, importlib-metadata, gitdb, ffmpeg-python, ctranslate2, contourpy, cffi, aiosignal, soundfile, scikit-learn, rich, pywhispercpp, pydeck, pyannote.core, pooch, pandas, nvidia-cusolver-cu11, nvidia-cudnn-cu11, matplotlib, jsonschema-specifications, hyperpyyaml, huggingface-hub, gitpython, dtw-python, alembic, aiohttp, transformers, optuna, librosa, jsonschema, ffsubsync, faster-whisper, pyannote.database, altair, streamlit, pyannote.pipeline, pyannote.metrics, streamlit-player, streamlit-aggrid, triton, torch, torchmetrics, torchaudio, torch-pitch-shift, pytorch-lightning, julius, torch-audiomentations, speechbrain, pytorch-metric-learning, lightning, asteroid-filterbanks, pyannote.audio, openai-whisper, whisperx, whisper-timestamped, dl-translate, subsai
  DEPRECATION: whisper-timestamped is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at https://github.com/pypa/pip/issues/8559
  Running setup.py install for whisper-timestamped ... done
Successfully installed Cython-3.0.4 Mako-1.2.4 MarkupSafe-2.1.3 aiohttp-3.8.6 aiosignal-1.3.1 alembic-1.12.1 altair-4.2.2 antlr4-python3-runtime-4.9.3 asteroid-filterbanks-0.4.0 async-timeout-4.0.3 attrs-23.1.0 audioread-3.0.1 auditok-0.1.5 av-10.0.0 blinker-1.6.3 cachetools-5.3.2 certifi-2023.7.22 cffi-1.16.0 chardet-5.2.0 charset-normalizer-3.3.1 click-8.1.7 cmake-3.27.7 colorama-0.4.6 colorlog-6.7.0 contourpy-1.1.1 ctranslate2-3.20.0 cycler-0.12.1 decorator-5.1.1 dl-translate-0.2.6 docopt-0.6.2 dtw-python-1.3.0 einops-0.7.0 entrypoints-0.4 faster-whisper-0.5.1 faust-cchardet-2.1.19 ffmpeg-python-0.2.0 ffsubsync-0.4.25 filelock-3.13.0 fonttools-4.43.1 frozenlist-1.4.0 fsspec-2023.10.0 future-0.18.3 gitdb-4.0.11 gitpython-3.1.40 greenlet-3.0.1 huggingface-hub-0.18.0 hyperpyyaml-1.2.2 idna-3.4 importlib-metadata-6.8.0 jinja2-3.1.2 joblib-1.3.2 jsonschema-4.19.1 jsonschema-specifications-2023.7.1 julius-0.2.7 kiwisolver-1.4.5 lazy-loader-0.3 librosa-0.10.1 lightning-2.1.0 lightning-utilities-0.9.0 lit-17.0.3 llvmlite-0.41.1 markdown-it-py-3.0.0 matplotlib-3.8.0 mdurl-0.1.2 more-itertools-10.1.0 mpmath-1.3.0 msgpack-1.0.7 multidict-6.0.4 networkx-3.2 nltk-3.8.1 numba-0.58.1 numpy-1.26.1 nvidia-cublas-cu11-11.10.3.66 nvidia-cuda-cupti-cu11-11.7.101 nvidia-cuda-nvrtc-cu11-11.7.99 nvidia-cuda-runtime-cu11-11.7.99 nvidia-cudnn-cu11-8.5.0.96 nvidia-cufft-cu11-10.9.0.58 nvidia-curand-cu11-10.2.10.91 nvidia-cusolver-cu11-11.4.0.1 nvidia-cusparse-cu11-11.7.4.91 nvidia-nccl-cu11-2.14.3 nvidia-nvtx-cu11-11.7.91 omegaconf-2.3.0 openai-whisper-20230124 optuna-3.4.0 packaging-23.2 pandas-1.5.3 pillow-10.1.0 platformdirs-3.11.0 pooch-1.8.0 primePy-1.3 protobuf-3.20.3 pyannote.audio-2.1.1 pyannote.core-5.0.0 pyannote.database-5.0.1 pyannote.metrics-3.2.1 pyannote.pipeline-3.0.1 pyarrow-13.0.0 pycparser-2.21 pydeck-0.8.1b0 pydub-0.25.1 pygments-2.16.1 pympler-1.0.1 pyparsing-3.1.1 pysubs2-1.6.1 python-dateutil-2.8.2 python-decouple-3.8 pytorch-lightning-2.1.0 pytorch-metric-learning-2.3.0 pytz-2023.3.post1 pywhispercpp-1.1.1 pyyaml-6.0.1 referencing-0.30.2 regex-2023.10.3 requests-2.31.0 rich-13.6.0 rpds-py-0.10.6 ruamel.yaml-0.18.2 ruamel.yaml.clib-0.2.8 safetensors-0.4.0 scikit-learn-1.3.2 scipy-1.11.3 semver-3.0.2 sentencepiece-0.1.99 shellingham-1.5.4 six-1.16.0 smmap-5.0.1 sortedcontainers-2.4.0 soundfile-0.12.1 soxr-0.3.7 speechbrain-0.5.15 sqlalchemy-2.0.22 srt-3.5.3 streamlit-1.20.0 streamlit-aggrid-0.3.4.post3 streamlit-player-0.1.5 subsai-1.2.1 sympy-1.12 tabulate-0.9.0 tensorboardX-2.6.2.2 threadpoolctl-3.2.0 tokenizers-0.13.3 toml-0.10.2 toolz-0.12.0 torch-2.0.1 torch-audiomentations-0.11.0 torch-pitch-shift-1.2.4 torchaudio-2.0.2 torchmetrics-1.2.0 tornado-6.3.3 tqdm-4.66.1 transformers-4.33.3 triton-2.0.0 typer-0.9.0 typing-extensions-4.8.0 tzlocal-5.2 urllib3-2.0.7 validators-0.22.0 watchdog-3.0.0 webrtcvad-2.0.10 wheel-0.41.2 whisper-timestamped-1.12.20 whisperx-3.1.1 yarl-1.9.2 zipp-3.17.0

(subsai2) root@snuminipc:~/subsai2# time subsai /mnt/a/1.mp4 --model m-bain/whisperX --format srt

[06:02:42] WARNING  torchvision is not available - cannot save figures                                          train_logger.py:227

███████╗██╗   ██╗██████╗ ███████╗     █████╗ ██╗
██╔════╝██║   ██║██╔══██╗██╔════╝    ██╔══██╗██║
███████╗██║   ██║██████╔╝███████╗    ███████║██║
╚════██║██║   ██║██╔══██╗╚════██║    ██╔══██║██║
███████║╚██████╔╝██████╔╝███████║    ██║  ██║██║
╚══════╝ ╚═════╝ ╚═════╝ ╚══════╝    ╚═╝  ╚═╝╚═╝
                                            
Subs AI: Subtitles generation tool powered by OpenAI's Whisper and its variants.
Version: 1.2.1               
===================================

[-] Model name: m-bain/whisperX
[-] Model configs: defaults
---
[+] Initializing the model
Traceback (most recent call last):
  File "/root/subsai2/bin/subsai", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/root/subsai2/lib/python3.11/site-packages/subsai/cli.py", line 149, in main
    run(media_file_arg=args.media_file,
  File "/root/subsai2/lib/python3.11/site-packages/subsai/cli.py", line 81, in run
    model = subs_ai.create_model(model_name, model_configs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai2/lib/python3.11/site-packages/subsai/main.py", line 96, in create_model
    return AVAILABLE_MODELS[model_name]['class'](model_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai2/lib/python3.11/site-packages/subsai/models/whisperX_model.py", line 123, in __init__
    self.model = whisperx.load_model(self.model_type,
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai2/lib/python3.11/site-packages/whisperx/asr.py", line 52, in load_model
    model = WhisperModel(whisper_arch,
            ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/subsai2/lib/python3.11/site-packages/faster_whisper/transcribe.py", line 120, in __init__
    self.model = ctranslate2.models.Whisper(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: __init__(): incompatible constructor arguments. The following argument types are supported:
    1. ctranslate2._ext.Whisper(model_path: str, device: str = 'cpu', *, device_index: Union[int, List[int]] = 0, compute_type: Union[str, Dict[str, str]] = 'default', inter_threads: int = 1, intra_threads: int = 0, max_queued_batches: int = 0, files: object = None)

Invoked with: '/root/.cache/huggingface/hub/models--guillaumekln--faster-whisper-base/snapshots/515102184abb526d1cfb9c882107192588d7250a'; kwargs: device=None, device_index=0, compute_type='default', intra_threads=4, inter_threads=1

real    0m9.619s
user    0m5.648s
sys     0m1.714s

Snuupy Oct 28, 2023
Author

I tried the following commits and they did not work either, same error:

m-bain/whisperX@dbeb861
m-bain/whisperX@0ae0d49 (default commit on subsai repo)
m-bain/whisperX@d8a2b4f (v3.1.1 May 13 release)

absadiki Oct 29, 2023
Maintainer

Thanks @Snuupy for the detailed answer.

It took me some time to figure it out .. I think you didn't provide the model_type with the command to WhisperX!
I think WhisperX does not fall back to the base model so you have to provide the model type as an argument.

Please try with the same command as in the Readme page, and just replace openai/whisper with whisperX, like the following:

subsai "/mnt/a/1.mp4" --model m-bain/whisperX --model-configs '{"model_type": "small"}' --format srt

let me know if that solved the issue ?

I believe I did set the defaults for WhisperX to take the base model as well. I will try to debug on my end as well.

absadiki Oct 29, 2023
Maintainer

Sorry @Snuupy, I was mistaken, I am the one who get crazy now lol

As I though, I did set all the models to take the base model by default, so you can use the model without specifying the model type.

After debugging, I found that I was setting the device to None as a default value, but faster-whisper requires a str.

Please pull the latest commit and give it a try now ?

Answer selected by Snuupy

Snuupy Oct 29, 2023
Author

Yup looks like it is working now. What a sneaky bug! :P

Thank you for building this wrapper so there is a uniform interface across the different types of implementations. I will try CUDA soon to see what kind of performance I can get out of my P3200 laptop GPU. I will let you know if I run into any more bugs! :)

absadiki Oct 30, 2023
Maintainer

Yeah really sneaky :P .. When I first wrote the wrapper around WhisperX, I though they are using the Pytorch implementation under the hood, and because I was testing with cuda all the time I didn't face that problem, but 'glad it is working now.

The P3200 GPU is good, you will get much more performance compared to the CPU. Feel free to let me know if you run into any issue :)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

whisperX doesn't work but faster-whisper does #77

{{title}}

Replies: 1 comment 6 replies

{{title}}

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{title}}

Select a reply

whisperX doesn't work but faster-whisper does #77

Snuupy Oct 27, 2023

Replies: 1 comment · 6 replies

absadiki Oct 28, 2023 Maintainer

Snuupy Oct 28, 2023 Author

Snuupy Oct 28, 2023 Author

absadiki Oct 29, 2023 Maintainer

absadiki Oct 29, 2023 Maintainer

Snuupy Oct 29, 2023 Author

absadiki Oct 30, 2023 Maintainer

Snuupy
Oct 27, 2023

Replies: 1 comment 6 replies

absadiki
Oct 28, 2023
Maintainer

Snuupy Oct 28, 2023
Author

Snuupy Oct 28, 2023
Author

absadiki Oct 29, 2023
Maintainer

absadiki Oct 29, 2023
Maintainer

Snuupy Oct 29, 2023
Author

absadiki Oct 30, 2023
Maintainer