Automatic Speech Recognition
Transformers
Safetensors
cohere_asr
audio
hf-asr-leaderboard
speech-recognition
transcription
custom_code
Instructions to use AEmotionStudio/cohere-transcribe-03-2026-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AEmotionStudio/cohere-transcribe-03-2026-models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="AEmotionStudio/cohere-transcribe-03-2026-models", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("AEmotionStudio/cohere-transcribe-03-2026-models", trust_remote_code=True) model = AutoModelForSpeechSeq2Seq.from_pretrained("AEmotionStudio/cohere-transcribe-03-2026-models", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Mirror CohereLabs/cohere-transcribe-03-2026 → AEmotionStudio/cohere-transcribe-03-2026-models
d114f70 verified | { | |
| "auto_map": { | |
| "AutoFeatureExtractor": "processing_cohere_asr.CohereAsrFeatureExtractor" | |
| }, | |
| "dither": 1e-05, | |
| "feature_extractor_type": "CohereAsrFeatureExtractor", | |
| "feature_size": 128, | |
| "frame_splicing": 1, | |
| "log": true, | |
| "n_fft": 512, | |
| "n_window_size": 400, | |
| "n_window_stride": 160, | |
| "normalize": "per_feature", | |
| "pad_to": 0, | |
| "padding_value": 0.0, | |
| "sampling_rate": 16000, | |
| "window": "hann" | |
| } | |