What WeST is
The model is described as an open-source speech recognition system that turns speech into text with a large language model in about 300 lines of code. It consists of an LLM, a speech encoder and a projector.
What you can do with it
- Swap the LLM for one such as LLaMA or QWen
- Encode speech with an encoder such as Whisper
- Configure training and test data in JSONL format
Application scenarios
- A developer builds a speech assistant prototype
- A researcher runs recognition experiments
- A teaching team demonstrates the mechanism
Pros & cons
✓ What we like
- Training parameters include learning rate and weight decay
- Deepspeed configuration is supported
! What to watch out for
- Only the projector part is trainable
- Training and test data must follow the JSONL format
FAQ
What is trainable?
The material states only the projector part can be trained.
What inspired the project?
The material names SLAM-ASR and LLaMA 3.1 as the inspiration.
Last reviewed: 2026-11-15
More AI audio tools tools
View all →-
Accent Guesser Accent recognition from a recording Free tools Creator tools Audio Speech to text Education tools -
AccurateScribe.ai Transcription for audio and video Free tools Creator tools Video to text Audio Speech to text -
Adobe Podcast Browser podcast recording and cleanup Free tools Creator tools Audio Speech to text Audio editing -
Agilotext French-first transcription and summaries Audio Speech to text Podcast Meeting transcription Meeting notes -
AI Dubbing Short video dubbing without signup Free tools Video translation Audio Voiceover Content localization -
AI Mastering Automatic online mastering Free tools Freemium tools Audio Podcast