yzGuu830/efficient-speech-codec
[EMNLP 2024] ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
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.
Stars
125
Forks
7
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
transformerlab/transformerlab-app
The open source research environment for AI researchers to seamlessly train, evaluate, and scale...
naru-project/naru
Neural Relation Understanding: neural cardinality estimators for tabular data
neurocard/neurocard
State-of-the-art neural cardinality estimators for join queries
danielzuegner/code-transformer
Implementation of the paper "Language-agnostic representation learning of source code from...
salesforce/CodeTF
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM