Automatic Speech Recognition
Transformers
Safetensors
Arabic
English
cohere_asr
arabic
code-switching
decoder-only-finetune
Instructions to use nsa01n/cohere-cs-decoder-middle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nsa01n/cohere-cs-decoder-middle with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nsa01n/cohere-cs-decoder-middle")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nsa01n/cohere-cs-decoder-middle") model = AutoModelForSpeechSeq2Seq.from_pretrained("nsa01n/cohere-cs-decoder-middle", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from nsa01n/cohere-cs-decoder-middle: direct link, hf CLI and curl.
- Browser
- Download file 580 Bytes
-
https://huggingface.co/nsa01n/cohere-cs-decoder-middle/resolve/main/processor_config.json
- Command line
-
hf download hf://nsa01n/cohere-cs-decoder-middle/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/nsa01n/cohere-cs-decoder-middle/resolve/main/processor_config.json
580 Bytes
| { | |
| "feature_extractor": { | |
| "auto_map": { | |
| "AutoProcessor": "processing_cohere_asr.CohereAsrProcessor" | |
| }, | |
| "dither": 1e-05, | |
| "feature_extractor_type": "CohereAsrFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "max_audio_clip_s": 35.0, | |
| "min_energy_window_samples": 1600, | |
| "n_fft": 512, | |
| "overlap_chunk_second": 5.0, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemphasis": 0.97, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "processor_class": "CohereAsrProcessor" | |
| } | |