transcribe-anything
whisperX
Our great sponsors
transcribe-anything | whisperX | |
---|---|---|
11 | 24 | |
342 | 8,965 | |
- | - | |
9.3 | 8.4 | |
17 days ago | 3 days ago | |
Python | Python | |
MIT License | BSD 4-Clause "Original" or "Old" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
transcribe-anything
-
Summarize audio recordings in text
transcribe-anything
-
$620,000 stolen from YouTuber Ethan Klein and the H3 Podcast by MCN BroadbandTV and their CEO Shahrzad Rafati
OpenAI whisper. Here is a tool that has it, a video downloader, and some other things bundled in with it: https://github.com/zackees/transcribe-anything
- 32 Open Source Libraries for Python's 32nd Birthday
-
Show HN: Self-host Whisper As a Service with GUI and queueing
People interested in this might also be interested in transcribe-anything [1].
It automates video fetching and uses whisper to generate .srt, .vtt and .txt files.
[1] https://github.com/zackees/transcribe-anything
-
[P] Free Youtube Subtitles Generator
Nice looks great, link broken but it just needed a hyphen https://github.com/zackees/transcribe-anything
-
Gpu accelerated ML apps will soon get a lot easier to deploy - Pytorch-cuda moving to 100% pypi hosting.
Right now the cuda accelerated whls are hosted outside of pypi which can only be accessed by using `--extra-index-url`, when installing from a requirements file (pip install -r requirements.txt). However pip install doesn't allow --extra-index-url for security reasons, which means deploying cuda accelerated ML apps on python is a complicated affair, see this [script](https://github.com/zackees/transcribe-anything/blob/main/install_cuda.py) as an example of what needs to be done to uninstall conflicting cpu only version of pytorch and replace it with cuda acceleration.
- Bro, listen: Interact with OpenAI using voice
- Convert YouTube to Text with OpenAI Whisper
-
Draw an owl
Transcribe Anything
-
Transcribe Video/Audio on the web using `transcribe-anything`, a front end to WhisperAI
Code Repo: https://github.com/zackees/transcribe-anything (please give my repo a like)
whisperX
-
Easy video transcription and subtitling with Whisper, FFmpeg, and Python
It uses this, which does support diarization: https://github.com/m-bain/whisperX
-
SOTA ASR Tooling: Long-Form Transcription
Author compared various whisper implementation
"We found that WhisperX is the best framework for transcribing long audio files efficiently and accurately. It’s much better than using the standard openai-whisper library."
https://github.com/m-bain/whisperX
-
Deploying whisperX on AWS SageMaker as Asynchronous Endpoint
import os # Directory and file paths dir_path = './models-v1' inference_file_path = os.path.join(dir_path, 'code/inference.py') requirements_file_path = os.path.join(dir_path, 'code/requirements.txt') # Create the directory structure os.makedirs(os.path.dirname(inference_file_path), exist_ok=True) # Inference.py content inference_content = '''# inference.py # inference.py import io import json import logging import os import tempfile import time import boto3 import torch import whisperx DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu' s3 = boto3.client('s3') def model_fn(model_dir, context=None): """ Load and return the WhisperX model necessary for audio transcription. """ print("Entering model_fn") logging.info("Loading WhisperX model") model = whisperx.load_model(whisper_arch=f"{model_dir}/guillaumekln/faster-whisper-large-v2", device=DEVICE, language="en", compute_type="float16", vad_options={'model_fp': f"{model_dir}/whisperx/vad/pytorch_model.bin"}) print("Loaded WhisperX model") print("Exiting model_fn with model loaded") return { 'model': model } def input_fn(request_body, request_content_type): """ Process and load audio from S3, given the request body containing S3 bucket and key. """ print("Entering input_fn") if request_content_type != 'application/json': raise ValueError("Invalid content type. Must be application/json") request = json.loads(request_body) s3_bucket = request['s3bucket'] s3_key = request['s3key'] # Download the file from S3 temp_file = tempfile.NamedTemporaryFile(delete=False) s3.download_file(Bucket=s3_bucket, Key=s3_key, Filename=temp_file.name) print(f"Downloaded audio from S3: {s3_bucket}/{s3_key}") print("Exiting input_fn") return temp_file.name def predict_fn(input_data, model, context=None): """ Perform transcription on the provided audio file and delete the file afterwards. """ print("Entering predict_fn") start_time = time.time() whisperx_model = model['model'] logging.info("Loading audio") audio = whisperx.load_audio(input_data) logging.info("Transcribing audio") transcription_result = whisperx_model.transcribe(audio, batch_size=16) try: os.remove(input_data) # input_data contains the path to the temp file print(f"Temporary file {input_data} deleted.") except OSError as e: print(f"Error: {input_data} : {e.strerror}") end_time = time.time() elapsed_time = end_time - start_time logging.info(f"Transcription took {int(elapsed_time)} seconds") print(f"Exiting predict_fn, processing took {int(elapsed_time)} seconds") return transcription_result def output_fn(prediction, accept, context=None): """ Prepare the prediction result for the response. """ print("Entering output_fn") if accept != "application/json": raise ValueError("Accept header must be application/json") response_body = json.dumps(prediction) print("Exiting output_fn with response prepared") return response_body, accept ''' # Write the inference.py file with open(inference_file_path, 'w') as file: file.write(inference_content) # Requirements.txt content requirements_content = '''speechbrain==0.5.16 faster-whisper==0.7.1 git+https://github.com/m-bain/whisperx.git@1b092de19a1878a8f138f665b1467ca21b076e7e ffmpeg-python ''' # Write the requirements.txt file with open(requirements_file_path, 'w') as file: file.write(requirements_content)
-
OpenVoice: Versatile Instant Voice Cloning
Whisper doesn't, but WhisperX <https://github.com/m-bain/whisperX/> does. I am using it right now and it's perfectly serviceable.
For reference, I'm transcribing research-related podcasts, meaning speech doesn't overlap a lot, which would be a problem for WhisperX from what I understand. There's also a lot of accents, which are straining on Whisper (though it's also doing well), but surely help WhisperX. It did have issues with figuring number of speakers on it's own, but that wasn't a problem for my use case.
- FLaNK 15 Jan 2024
-
Subtitle is now open-source
I've had good results with whisperx when I needed to generate captions. https://github.com/m-bain/whisperX
There is currently a problem with diarization, but otherwise, it is SOTA.
-
Insanely Fast Whisper: Transcribe 300 minutes of audio in less than 98 seconds
https://github.com/m-bain/whisperX/issues/569
WhisperX with the new model. It's not fast.
-
Distil-Whisper: distilled version of Whisper that is 6 times faster, 49% smaller
How much faster in real wall-clock time is this in batched data than https://github.com/m-bain/whisperX ?
-
whisper self hosted what's the most cost-efficient way
Checkout whisperx
-
Whisper Turbo: transcribe 20x faster than realtime using Rust and WebGPU
Neat to see a new implementation, although I'll note that for those looking for a drop-in replacement for the whisper library, I believe that both faster-whisper https://github.com/guillaumekln/faster-whisper and https://github.com/m-bain/whisperX are easier (PyTorch-based, doesn't require a web browser), and a lot faster (WhisperX is up to 70X realtime).
What are some alternatives?
frogbase - Transform audio-visual content into navigable knowledge.
whisper.cpp - Port of OpenAI's Whisper model in C/C++
Hentai-Diffusion - The official place for the best A.I.
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
subtitle-generator - Generate subtitles for youtube videos for free with https://text-generator.io
faster-whisper - Faster Whisper transcription with CTranslate2
static_ffmpeg - Installs FFMPEG v5 On Win32/Ubuntu/MacOS
insanely-fast-whisper - Incredibly fast Whisper-large-v3
ai-notes - notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.
openai-whisper-cpu - Improving transcription performance of OpenAI Whisper for CPU based deployment
DeepSpeech-examples - Examples of how to use or integrate DeepSpeech
ControlNet - Let us control diffusion models!