Instructions to use Matthijs/mms-tts-deu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Matthijs/mms-tts-deu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="Matthijs/mms-tts-deu")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("Matthijs/mms-tts-deu") model = AutoModelForTextToWaveform.from_pretrained("Matthijs/mms-tts-deu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Matthijs/mms-tts-deu: direct link, hf CLI and curl.
- Browser
- Download file 248 Bytes
-
https://huggingface.co/Matthijs/mms-tts-deu/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Matthijs/mms-tts-deu/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Matthijs/mms-tts-deu/resolve/main/tokenizer_config.json
248 Bytes
| { | |
| "add_blank": true, | |
| "clean_up_tokenization_spaces": true, | |
| "language": "deu", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "phonemize": false, | |
| "tokenizer_class": "VitsTokenizer", | |
| "unk_token": "<unk>" | |
| } | |