Instructions to use voidful/hubert-tiny-unit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use voidful/hubert-tiny-unit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="voidful/hubert-tiny-unit")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("voidful/hubert-tiny-unit") model = AutoModelForCTC.from_pretrained("voidful/hubert-tiny-unit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 291 Bytes
8e8967d | 1 2 3 4 5 6 7 8 9 10 11 12 | {
"bos_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"replace_word_delimiter_char": " ",
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": "|"
}
|