Downloads · 30 days
22
12% of all-time downloads
whisper-nepali-audio
mandeep111/whisper-nepali-audio
whisper-nepali-audio is a automatic speech recognition model from mandeep111. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Fine-tuned on 98 high-quality clips (~60% Nepali, 25% mixed Nepali-English, 15% English) from speaker.
All-time downloads
189
Public
Parameters
242M
2.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.9 GB · 66%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 22, 2025
- Updated
- Nov 22, 2025
- SHA
- dfeb3f49
Model card
From the Hugging Face model README
Whisper Small – Nepali + English Code-Switching (Nepali Voice)
Fine-tuned on 98 high-quality clips (~60% Nepali, 25% mixed Nepali-English, 15% English) from speaker.
Perfect for transcribing natural Nepali conversations with English words mixed in.
Usage
from transformers import pipeline
asr = pipeline("automatic-speech-recognition", model="mandeep111/whisper-nepali-audio")
asr("your_nepali_audio.wav")
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- apache-2.0
- Languages
- ne
- Created
- Nov 22, 2025
- Updated
- Nov 22, 2025