Tiron is an open-weights model based on Whisper for automatic speech recognition with multi-speaker support and speaker diarization. Hosted on Hugging Face, it enables developers to run local or hosted transcription of meetings and conversations. The model is designed for accurate attribution of spoken content among multiple participants.
In the AI & ML space, Tiron takes a focused approach. Accurately transcribing and attributing speech in multi-speaker meetings using open models. It is built as an open-source project for developers. Tiron is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
It is developed by Trelis, and it first shipped in 2026. Development happens publicly on GitHub with 6 commits in the last 90 days. Among its 4 catalogued features are Multi-speaker Transcription, Speaker Diarization, and whisper-based.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match