ga642381/AudioCodec-Hub
AudioCodec-Hub is a Python library for encoding and decoding audio data, supporting various neural audio codec models
This tool helps machine learning researchers working with speech and language models efficiently prepare audio data. It takes your raw audio files, either individually or in batches from a directory, and converts them into a compressed, numerical representation (encoded data). This encoded data can then be used for training large speech models, and the tool can also reconstruct audio from these numerical codes. It's designed for researchers needing to manage and process large audio datasets.
No commits in the last 6 months.
Use this if you are an AI/ML researcher who needs to encode large collections of audio files into a compressed format for training speech or language models, or to decode them back into audio waveforms.
Not ideal if you are looking for a general-purpose audio converter for everyday use, or if you need to process multi-channel audio files, as that feature is not yet supported.
Stars
25
Forks
2
Language
Python
License
MIT
Category
Last pushed
Sep 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ga642381/AudioCodec-Hub"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.