Instructions to use valoomba/granite-speech-4.1-2b-plus-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use valoomba/granite-speech-4.1-2b-plus-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('automatic-speech-recognition', 'valoomba/granite-speech-4.1-2b-plus-ONNX');
Download processor_config.json from valoomba/granite-speech-4.1-2b-plus-ONNX: direct link, hf CLI and curl.
- Browser
- Download file 415 Bytes
-
https://huggingface.co/valoomba/granite-speech-4.1-2b-plus-ONNX/resolve/main/processor_config.json
- Command line
-
hf download hf://valoomba/granite-speech-4.1-2b-plus-ONNX/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/valoomba/granite-speech-4.1-2b-plus-ONNX/resolve/main/processor_config.json
415 Bytes
| { | |
| "audio_processor": { | |
| "feature_extractor_type": "GraniteSpeechFeatureExtractor", | |
| "melspec_kwargs": { | |
| "hop_length": 160, | |
| "n_fft": 512, | |
| "n_mels": 80, | |
| "sample_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "projector_downsample_rate": 5, | |
| "projector_window_size": 15, | |
| "sampling_rate": 16000 | |
| }, | |
| "audio_token": "<|audio|>", | |
| "processor_class": "GraniteSpeechProcessor" | |
| } | |