Instructions to use Matir/granite-speech-4.1-2b-plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Matir/granite-speech-4.1-2b-plus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Matir/granite-speech-4.1-2b-plus")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Matir/granite-speech-4.1-2b-plus") model = AutoModelForSpeechSeq2Seq.from_pretrained("Matir/granite-speech-4.1-2b-plus") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": false, | |
| "audio_token": "<|audio|>", | |
| "backend": "tokenizers", | |
| "bos_token": "<|end_of_text|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|end_of_text|>", | |
| "errors": "replace", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "model_specific_special_tokens": { | |
| "audio_token": "<|audio|>" | |
| }, | |
| "pad_token": "<|pad|>", | |
| "padding_side": "left", | |
| "processor_class": "GraniteSpeechProcessor", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "<|unk|>" | |
| } | |