Downloads · 30 days
0
cohere-transcribe-03-2026-onnx
eschmidbauer/cohere-transcribe-03-2026-onnx
cohere-transcribe-03-2026-onnx is a machine learning model from eschmidbauer. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
ONNX export of CohereLabs/cohere-transcribe-03-2026 for inference without PyTorch.
Access
Public
Updated Apr 1, 2026
Repo size
8.3 GB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.onnx8.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Apr 1, 2026
- SHA
- eb9b9b5d
Model card
From the Hugging Face model README
Cohere Transcribe 03-2026 (ONNX)
ONNX export of CohereLabs/cohere-transcribe-03-2026 for inference without PyTorch.
Architecture
The model is split into three logical stages, all self-contained .onnx files:
| File | Role | Size |
|---|---|---|
encoder-0.onnx | Conv subsampling + positional encoding + conformer layers 0-8 | ~1.3 GB |
encoder-1.onnx | Conformer layers 9-16 | ~1.3 GB |
encoder-2.onnx | Conformer layers 17-24 | ~1.3 GB |
encoder-3.onnx | Conformer layers 25-32 + encoder-decoder projection | ~1.3 GB |
cross_kv.onnx | Project encoder output to cross-attention K/V for all 8 decoder layers | ~72 MB |
decoder.onnx | Autoregressive transformer decoder with KV cache | ~580 MB |
Inference pipeline: mel features → encoder splits (chained) → cross_kv → decoder (autoregressive loop).
Setup
pip install onnx onnxruntime torch transformers librosa soundfile sentencepiece datasets torchcodec
Export
python export_onnx.py
Transcribe
python transcribe.py # download random en/es demo samples and transcribe
python transcribe.py audio.wav
python transcribe.py audio_dir/
python transcribe.py audio.wav es # language code
Output includes per-file RTF (real-time factor). RTF < 1.0 means faster than real-time.
- License
- apache-2.0
- Created
- Mar 26, 2026
- Updated
- Apr 1, 2026