hitz-zentroa/whisper-lm
Add n-gram and large language model (LLM) support to Whisper models.
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.
Stars
41
Forks
4
Language
Jupyter Notebook
License
Apache-2.0
Category
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.
Higher-rated alternatives
NX-AI/xlstm
Official repository of the xLSTM.
sinanuozdemir/oreilly-hands-on-gpt-llm
Mastering the Art of Scalable and Efficient AI Model Deployment
DashyDashOrg/pandas-llm
Pandas-LLM
wxhcore/bumblecore
An LLM training framework built from the ground up, featuring a custom BumbleBee architecture...
MiniMax-AI/MiniMax-01
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model &...