vapoursynth
whisperX
Our great sponsors
vapoursynth | whisperX | |
---|---|---|
10 | 24 | |
1,534 | 8,965 | |
2.7% | - | |
9.2 | 8.4 | |
4 days ago | 5 days ago | |
C++ | Python | |
GNU Lesser General Public License v3.0 only | 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.
vapoursynth
- FLaNK 15 Jan 2024
- FFmpeg is getting better with multithreaded transcoding pipelines
-
Ffmprovisr – Making FFmpeg Easier
Since ffmpeg CLI still makes me pull ny hair out, I am going to plug vapoursynth:
https://www.vapoursynth.com/
Its Pythonic video filters... But also so much more: https://vsdb.top/
And Staxrip, which makes such good use of ffmpeg, vapoursynth, and dozens of other encoders and tools that I reboot from linux to Windows just to use it: https://github.com/staxrip/staxrip
-
[Guide] Installing av1an on Ubuntu 22.04
git clone https://github.com/vapoursynth/vapoursynth cd vapoursynth ./configure make sudo make install
-
Im making a video editor in Python. Yes, i'm crazy. No, it wont lag
Are you aware of Vapoursynth? https://www.vapoursynth.com/
-
Fast Real Time JavaScript Video Manipulation / Postprocessing
I have a few options here to process the individual frames for example using ImageData, which exposes the data as an array of pixels, so you could easily 'borrow' some VapourSynth filters for this:
-
AV1 encoder for Linux
Does the name AviSynth mean anything to you? If so and you want a similar Linux native tool "inspired" by AviSynth, to quote the website, check out http://www.vapoursynth.com/ Just bear in mind that the scripting language is different.
-
NVIDIA Optical Flow CUDA interface: CUarray vs CUdeviceptr
I'm a total newbie to CUDA. I'm trying to implement NVOF in VapourSynth video processing framework. I got the NVOF context initialized. Next step is the buffers!
-
How to compile Av1an on Windows without breaking your eggs
Download vapoursynth r57 portable from https://github.com/vapoursynth/vapoursynth/releases it's a 7z file so you should have 7-zip installed
-
[Guild] How to compile Av1an on Ubuntu 21.04
Download and compile vapoursynth 1) Go to vapoursynth’s gihub (https://github.com/vapoursynth/vapoursynth/releases) download/wget the tar.gz 2) extract it with tar -xf 3) cd into the folder 4) sudo ./autogen.sh 5) sudo ./configure 6) sudo make install
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?
Av1an - Cross-platform command-line AV1 / VP9 / HEVC / H264 encoding framework with per scene quality encoding
whisper.cpp - Port of OpenAI's Whisper model in C/C++
moviepy - Video editing with Python
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
ffmpeg-python - Python bindings for FFmpeg - with complex filtering support
faster-whisper - Faster Whisper transcription with CTranslate2
staxrip - 🎞 Video encoding GUI for Windows.
insanely-fast-whisper - Incredibly fast Whisper-large-v3
vidcutter - A modern yet simple multi-platform video cutter and joiner.
openai-whisper-cpu - Improving transcription performance of OpenAI Whisper for CPU based deployment
FFMPerative - Chat to Compose Video
ControlNet - Let us control diffusion models!