Automatic Speech Recognition
Transformers
OpenVINO
audio
hf-asr-leaderboard
speech-recognition
transcription
Instructions to use Aditya02/cohere-transcribe-03-2026-ov-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aditya02/cohere-transcribe-03-2026-ov-fp16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Aditya02/cohere-transcribe-03-2026-ov-fp16")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Aditya02/cohere-transcribe-03-2026-ov-fp16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "feature_extractor": { | |
| "auto_map": { | |
| "AutoFeatureExtractor": "processing_cohere_asr.CohereAsrFeatureExtractor" | |
| }, | |
| "dither": 1e-05, | |
| "feature_extractor_type": "CohereAsrFeatureExtractor", | |
| "feature_size": 128, | |
| "frame_splicing": 1, | |
| "hop_length": 160, | |
| "log": true, | |
| "max_audio_clip_s": 35.0, | |
| "min_energy_window_samples": 1600, | |
| "n_fft": 512, | |
| "n_window_size": 400, | |
| "n_window_stride": 160, | |
| "normalize": "per_feature", | |
| "overlap_chunk_second": 5.0, | |
| "pad_to": 0, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemphasis": 0.97, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "processor_class": "CohereAsrProcessor" | |
| } | |