Downloads · 30 days
8
8% of all-time downloads
cohere-transcribe-03-2026-CoreML-fp16
BarathwajAnandan/cohere-transcribe-03-2026-CoreML-fp16
cohere-transcribe-03-2026-CoreML-fp16 is a automatic speech recognition model from BarathwajAnandan. Use it when you need speech turned into text. It is set up for coreml. The card lists the license as gpl-3.0.
This is a CoreML conversion of CohereLabs/cohere-transcribe-03-2026 using FP16 weights for on-device speech recognition on Apple Silicon.
All-time downloads
102
Public
Repo size
4.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin4.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- coreml
- License
- gpl-3.0
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026
- SHA
- ded49256
Base models
Model card
From the Hugging Face model README
Cohere Transcribe 03-2026 - CoreML (FP16)
This is a CoreML conversion of CohereLabs/cohere-transcribe-03-2026 using FP16 weights for on-device speech recognition on Apple Silicon.
Files
cohere_frontend.mlpackagecohere_encoder.mlpackagecohere_decoder_fullseq_masked.mlpackagecohere_decoder_cached.mlpackagecoreml_manifest.json
Usage
Load the .mlpackage artifacts in Xcode and use coreml_manifest.json for tokenizer and pipeline settings.
License
This converted model is released under GPL-3.0.
The upstream base model, CohereLabs/cohere-transcribe-03-2026, is Apache-2.0 licensed. This repo contains the CoreML conversion artifacts.
- Task
- Automatic Speech Recognition
- Library
- coreml
- License
- gpl-3.0
- Languages
- en, ar, de, el, es, fr
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026