Instructions to use moonshine-ai/moonshine-streaming-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moonshine-ai/moonshine-streaming-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="moonshine-ai/moonshine-streaming-medium")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("moonshine-ai/moonshine-streaming-medium", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from moonshine-ai/moonshine-streaming-medium: direct link, hf CLI and curl.
- Browser
- Download file 172 Bytes
-
https://huggingface.co/moonshine-ai/moonshine-streaming-medium/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://moonshine-ai/moonshine-streaming-medium/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/moonshine-ai/moonshine-streaming-medium/resolve/main/tokenizer_config.json
172 Bytes
| { | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "model_max_length": 4096, | |
| "unk_token": "<unk>", | |
| "bos_token": "<s>", | |
| "eos_token": "</s>", | |
| "pad_token": "<unk>" | |
| } | |