Model Description 🫐
This model is a fine-tuned version of Wav2Vec2-BERT 2.0 for Shona automatic speech recognition (ASR). It was trained on 72 hours of transcribed Shona speech. The ASR model is robust and the in-domain WER is below 23%.
- Developed by: Badr al-Absi
- Model type: Speech Recognition (ASR)
- Language: Shona (sn)
- License: CC-BY-4.0
- Finetuned from: facebook/w2v-bert-2.0
Direct Use
The model can be used directly for automatic speech recognition of a Shona audio:
from transformers import Wav2Vec2BertProcessor, Wav2Vec2BertForCTC
import torch
import torchaudio
# load model and processor
processor = Wav2Vec2BertProcessor.from_pretrained("badrex/w2v-bert-2.0-shona-asr")
model = Wav2Vec2BertForCTC.from_pretrained("badrex/w2v-bert-2.0-shona-asr")
# load audio
audio_input, sample_rate = torchaudio.load("path/to/audio.wav")
# preprocess
inputs = processor(audio_input.squeeze(), sampling_rate=sample_rate, return_tensors="pt")
# inference
with torch.no_grad():
logits = model(**inputs).logits
# decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)[0]
print(transcription)
Downstream Use
This model can be used as a foundation for:
- building voice assistants for Shona speakers
- transcription services for Shona content
- accessibility tools for Shona-speaking communities
- research in low-resource speech recognition
Model Architecture
- Base model: Wav2Vec2-BERT 2.0
- Architecture: transformer-based with convolutional feature extractor
- Parameters: ~600M (inherited from base model)
- Objective: connectionist temporal classification (CTC)
Funding
The development of this model was supported by CLEAR Global and Gates Foundation.
Citation
@misc{w2v_bert_shona_asr,
author = {Badr M. Abdullah},
title = {Adapting Wav2Vec2-BERT 2.0 for Shona ASR},
year = {2025},
publisher = {Hugging Face},
url = {https://huggingface.co/badrex/w2v-bert-2.0-shona-asr}
}
Model Card Contact
For questions or issues, please contact via the Hugging Face model repository in the community discussion section.