Automatic Speech Recognition
Transformers
Safetensors
English
Chinese
multilingual
whisper
multi-speaker
speaker-diarization
meeting-transcription
asr
Instructions to use Trelis/tiron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Trelis/tiron with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Trelis/tiron")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Trelis/tiron") model = AutoModelForSpeechSeq2Seq.from_pretrained("Trelis/tiron", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Tiron update 23 July 2026: v2 weights (small performance gains) + expanded benchmarks (MOSS, AssemblyAI u3.5-pro), published eval set + replication scripts, measurement-uncertainty notes
90bc0a4 verified 
- Xet hash:
- 740f9d9228572455c7d8e2bedc313e83d17d75b2846c49d0231dee47962062f2
- Size of remote file:
- 115 kB
- SHA256:
- 5f88001412056d71700473c137968bd12774909ebb9afb3f3a6e6777e40d3dc4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.