yzGuu830/efficient-speech-codec

[EMNLP 2024] ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers

35
/ 100
Emerging

This tool helps you shrink the file size of spoken audio recordings without losing significant sound quality. You put in a standard audio file (like a WAV), and it outputs a much smaller coded file and a reconstructed audio file that sounds very similar to the original. This is ideal for anyone working with large volumes of speech data, such as researchers, podcasters, or telecommunication professionals, who need efficient storage or transmission.

125 stars. No commits in the last 6 months.

Use this if you need to significantly reduce the file size of speech audio while maintaining good perceptual quality for storage, streaming, or bandwidth-constrained applications.

Not ideal if you need to compress music or complex audio, as this tool is specifically optimized for human speech.

speech-compression audio-storage voice-communication podcast-production research-data-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

125

Forks

7

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/yzGuu830/efficient-speech-codec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.