hitz-zentroa/whisper-lm

Add n-gram and large language model (LLM) support to Whisper models.

35
/ 100
Emerging

This project helps researchers and developers improve automatic speech recognition (ASR) accuracy, especially for languages with limited data. By combining audio input with n-gram or large language models, it produces more accurate text transcriptions. This is ideal for those working on speech-to-text systems for less common languages.

No commits in the last 6 months.

Use this if you are a researcher or developer working to improve the accuracy of speech-to-text models for low-resource languages by integrating external language models.

Not ideal if you are looking for a simple, out-of-the-box speech-to-text application for common languages, as this tool requires technical setup and expertise in ASR and language modeling.

speech-to-text language-technology computational-linguistics natural-language-processing low-resource-languages
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

41

Forks

4

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

May 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hitz-zentroa/whisper-lm"

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