Downloads · 30 days
10
9% of all-time downloads
mms-1b-asr-sna
HuggingAnalist/mms-1b-asr-sna
mms-1b-asr-sna is a automatic speech recognition model from HuggingAnalist. Use it when you need speech turned into text. It is set up for transformers.
facebook/mms-300m fine-tuned (character CTC head) on WaxalNLP snaasr for the Waxal ASR challenge. Trained in bf16/fp32 with ctczeroinfinity=True.
All-time downloads
116
Public
Parameters
963M
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026
- SHA
- 6f230e75
Model card
From the Hugging Face model README
MMS-300M — 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).
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Languages
- sna
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026