Instructions to use Vijish/mms with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vijish/mms with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Vijish/mms")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForPreTraining tokenizer = AutoTokenizer.from_pretrained("Vijish/mms") model = AutoModelForPreTraining.from_pretrained("Vijish/mms", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Vijish/mms: direct link, hf CLI and curl.
- Browser
- Download file 670 Bytes
-
https://huggingface.co/Vijish/mms/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Vijish/mms/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Vijish/mms/resolve/main/tokenizer_config.json
670 Bytes
| { | |
| "add_blank": true, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "|", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "64": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "is_uroman": false, | |
| "language": "mon", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "normalize": true, | |
| "pad_token": "|", | |
| "phonemize": false, | |
| "tokenizer_class": "VitsTokenizer", | |
| "unk_token": "<unk>", | |
| "verbose": false | |
| } | |