Downloads · 30 days
8
4% of all-time downloads
Sadou/mms-1b-wolof-finetuned
mms-1b-wolof-finetuned is a automatic speech recognition model from Sadou. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Fine-tuned version of facebook/mms-1b-all for Wolof Automatic Speech Recognition (ASR).
Downloads · 30 days
8
4% of all-time downloads
All-time downloads
200
Public
Parameters
965M
3.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.9 GB · 100%
From the Hugging Face model README
Fine-tuned version of facebook/mms-1b-all for Wolof Automatic Speech Recognition (ASR).
This model transcribes Wolof speech audio into Wolof text. It's the result of full fine-tuning (all 964M parameters) on 20,000 quality-filtered audio samples.
| Metric | Value |
|---|---|
| WER (Word Error Rate) | 29.56% |
| Test set | 500 examples |
| Training samples | 20,000 |
| Total audio | 25.6 hours |
| Mode | Full fine-tuning (964M params) |
from transformers import Wav2Vec2ForCTC, AutoProcessor
import torch
import torchaudio
# Load model and processor
model_id = "Sadou/mms-1b-wolof-finetuned"
processor = AutoProcessor.from_pretrained(model_id)
model = Wav2Vec2ForCTC.from_pretrained(model_id)
# Load audio (must be 16kHz, mono)
waveform, sr = torchaudio.load("your_audio.wav")
if sr != 16000:
waveform = torchaudio.transforms.Resample(sr, 16000)(waveform)
if waveform.shape[0] > 1:
waveform = waveform.mean(dim=0, keepdim=True)
# Transcribe
inputs = processor(waveform[0].numpy(), sampling_rate=16000, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)[0]
print(f"Transcription: {transcription}")
facebook/mms-1b-all| Step | WER | Phase |
|---|---|---|
| 300 | 47.67% | Initial training |
| 900 | 38.86% | |
| 1500 | 33.35% | |
| 2100 | 30.77% | |
| 2400 | 30.11% | Plateau detected |
| 2700 | 30.56% | LR decay started |
| 3300 | 29.56% | |
| 3600 | 29.56% | Final ✅ |
For audios longer than 30 seconds, use HuggingFace pipeline with chunking:
from transformers import pipeline
pipe = pipeline(
'automatic-speech-recognition',
model="Sadou/mms-1b-wolof-finetuned",
chunk_length_s=30,
stride_length_s=(4, 2),
device=0,
)
result = pipe("long_audio.wav")
print(result['text'])
@misc{wolof-mms-2026,
author = {Sadou Barry},
title = {MMS-1B Wolof Fine-Tuned},
year = {2026},
publisher = {HuggingFace},
url = {https://huggingface.co/Sadou/mms-1b-wolof-finetuned}
}