Automatic Speech Recognition
Transformers
Safetensors
English
moonshine
quantization-aware-training
int8
riscv
edge
Instructions to use CobbledSteel/moonshine-tiny-qat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CobbledSteel/moonshine-tiny-qat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="CobbledSteel/moonshine-tiny-qat")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("CobbledSteel/moonshine-tiny-qat") model = AutoModelForSpeechSeq2Seq.from_pretrained("CobbledSteel/moonshine-tiny-qat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from CobbledSteel/moonshine-tiny-qat: direct link, hf CLI and curl.
- Browser
- Download file 215 Bytes
-
https://huggingface.co/CobbledSteel/moonshine-tiny-qat/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://CobbledSteel/moonshine-tiny-qat/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/CobbledSteel/moonshine-tiny-qat/resolve/main/preprocessor_config.json
215 Bytes
| { | |
| "do_normalize": false, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |