Downloads · 30 days
8
15% of all-time downloads
SWECHA_GONTHUKA_ASR_finetune
dalavaihemanth/SWECHA_GONTHUKA_ASR_finetune
SWECHA_GONTHUKA_ASR_finetune is a automatic speech recognition model from dalavaihemanth. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is fine-tuned from swechatelangana/swecha-gonthuka-asr on a custom Telugu speech dataset.
All-time downloads
55
Public
Parameters
94.4M
378 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- e18d0333
Base models
Model card
From the Hugging Face model README
SWECHA GONTHUKA ASR Fine-tuned
This model is fine-tuned from swechatelangana/swecha-gonthuka-asr on a custom Telugu speech dataset.
Dataset
- 4911 Telugu audio recordings
- 16 kHz WAV files
- Multiple speakers
Base Model
swechatelangana/swecha-gonthuka-asr
Training
- Framework: Hugging Face Transformers
- Model: Wav2Vec2ForCTC
Usage
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
processor = Wav2Vec2Processor.from_pretrained(
"dalavaihemanth/SWECHA_GONTHUKA_ASR_finetune"
)
model = Wav2Vec2ForCTC.from_pretrained(
"dalavaihemanth/SWECHA_GONTHUKA_ASR_finetune"
)
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- te
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026