Instructions to use facebook/mms-tts-aka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-tts-aka with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="facebook/mms-tts-aka")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-aka") model = AutoModelForTextToWaveform.from_pretrained("facebook/mms-tts-aka", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update vocab.json
#2
by FarmerlineML - opened
Since MMS is unable to accurately capture numerals, the following is the structure of the vocab.json file. This format was derived from a 100-hour Akan audio dataset used during our ASR and TTS training.