Automatic Speech Recognition
Transformers
Safetensors
cohere_asr
audio
hf-asr-leaderboard
speech-recognition
transcription
custom_code
Eval Results
Instructions to use CohereLabs/cohere-transcribe-03-2026 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CohereLabs/cohere-transcribe-03-2026 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="CohereLabs/cohere-transcribe-03-2026", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("CohereLabs/cohere-transcribe-03-2026", trust_remote_code=True) model = AutoModelForSpeechSeq2Seq.from_pretrained("CohereLabs/cohere-transcribe-03-2026", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
pipeline_detokenization on Windows
#13
by Anthonyy232 - opened
Pretty sure pipeline_detokenization tweaks out and doesn't work on Windows because no fork()
Hi! We recommend you try the huggingface native implementation in transformers >=5.4.0. The tokenizer is much faster now which means we don't need pipeline_detokenization (and this option isn't present in the transformers version)