Instructions to use HuggingAnalist/mms-1b-asr-sna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HuggingAnalist/mms-1b-asr-sna with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="HuggingAnalist/mms-1b-asr-sna")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("HuggingAnalist/mms-1b-asr-sna") model = AutoModelForCTC.from_pretrained("HuggingAnalist/mms-1b-asr-sna") - Notebooks
- Google Colab
- Kaggle
MMS-300M โ Shona ASR
facebook/mms-300m fine-tuned (character CTC head) on WaxalNLP sna_asr for the Waxal ASR challenge. Trained in bf16/fp32 with ctc_zero_infinity=True.
language_model/lm_sna.arpa is a KenLM 4-gram built from the training transcriptions, for beam-search decoding with pyctcdecode (tune alpha/beta on validation).
- Downloads last month
- -