Downloads · 30 days
20
7% of all-time downloads
gujarati-asr
aijadugar/gujarati-asr
gujarati-asr is a machine learning model from aijadugar. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Gujarati Automatic Speech Recognition model trained using wav2vec2.
All-time downloads
277
Public
Parameters
316M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Model type
- wav2vec2
- Access
- Public
- Created
- May 29, 2026
- Updated
- Jun 1, 2026
- SHA
- 684414f4
Model card
From the Hugging Face model README
Gujarati ASR
Gujarati Automatic Speech Recognition model trained using wav2vec2.
Model Details
- Base Model: facebook/wav2vec2-large-xlsr-53
- Task: Gujarati Speech Recognition
- Language: Gujarati
- Sampling Rate: 16kHz
- Vocabulary Size: 102
Dataset
- ylacombe/google-gujarati
- Male + Female subsets combined
Features
- Gujarati speech → Gujarati text
- Supports male and female voices
- Fine-tuned on Gujarati audio-text pairs
Usage
from transformers import Wav2Vec2Processor
from transformers import Wav2Vec2ForCTC
processor = Wav2Vec2Processor.from_pretrained("aijadugar/gujarati-asr")
model = Wav2Vec2ForCTC.from_pretrained("aijadugar/gujarati-asr")
Author
Bari Ankit Vinod
- Type
- wav2vec2
- Created
- May 29, 2026
- Updated
- Jun 1, 2026