Instructions to use mazesmazes/tiny-audio-granite-gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mazesmazes/tiny-audio-granite-gemma with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="mazesmazes/tiny-audio-granite-gemma", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mazesmazes/tiny-audio-granite-gemma", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from mazesmazes/tiny-audio-granite-gemma: direct link, hf CLI and curl.
- Browser
- Download file 457 Bytes
-
https://huggingface.co/mazesmazes/tiny-audio-granite-gemma/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://mazesmazes/tiny-audio-granite-gemma/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/mazesmazes/tiny-audio-granite-gemma/resolve/main/preprocessor_config.json
457 Bytes
| { | |
| "delta_win_length": 3, | |
| "feature_extractor_type": "GraniteSpeech5FeatureExtractor", | |
| "feature_size": 320, | |
| "hop_length": 160, | |
| "logmel_floor_db": 8.0, | |
| "n_fft": 512, | |
| "num_mel_bins": 80, | |
| "padding": false, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400, | |
| "processor_class": "ASRProcessor", | |
| "auto_map": { | |
| "AutoProcessor": "asr_processing.ASRProcessor" | |
| } | |
| } |