Automatic Speech Recognition
Transformers
Safetensors
Welsh
English
moonshine
welsh
speech-recognition
vocabulary-pruning
Eval Results (legacy)
Instructions to use rebreda/moonshine-tiny-welsh-pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rebreda/moonshine-tiny-welsh-pruned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="rebreda/moonshine-tiny-welsh-pruned")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("rebreda/moonshine-tiny-welsh-pruned") model = AutoModelForSpeechSeq2Seq.from_pretrained("rebreda/moonshine-tiny-welsh-pruned", device_map="auto") - Notebooks
- Google Colab
- Kaggle
ghjjccx
Upload moonshine-tiny-welsh-pruned: weights, tokenizer, config and model card
bac3a13 verified Download generation_config.json from rebreda/moonshine-tiny-welsh-pruned: direct link, hf CLI and curl.
- Browser
- Download file 920 Bytes
-
https://huggingface.co/rebreda/moonshine-tiny-welsh-pruned/resolve/main/generation_config.json
- Command line
-
hf download hf://rebreda/moonshine-tiny-welsh-pruned/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/rebreda/moonshine-tiny-welsh-pruned/resolve/main/generation_config.json
920 Bytes
| { | |
| "_from_model_config": false, | |
| "assistant_confidence_threshold": 0.4, | |
| "assistant_lookbehind": 10, | |
| "bos_token_id": 1, | |
| "decoder_start_token_id": 1, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "encoder_repetition_penalty": 1.0, | |
| "eos_token_id": 2, | |
| "epsilon_cutoff": 0.0, | |
| "eta_cutoff": 0.0, | |
| "length_penalty": 1.0, | |
| "max_length": 194, | |
| "min_length": 0, | |
| "no_repeat_ngram_size": 0, | |
| "num_assistant_tokens": 20, | |
| "num_assistant_tokens_schedule": "constant", | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "pad_token_id": 2, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict_in_generate": false, | |
| "target_lookbehind": 10, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "transformers_version": "5.21.0", | |
| "typical_p": 1.0, | |
| "use_cache": true | |
| } | |