Downloads · 30 days
37
11% of all-time downloads
stt_hi_conformer_ctc_large_with_meta
WhissleAI/stt_hi_conformer_ctc_large_with_meta
stt_hi_conformer_ctc_large_with_meta is a machine learning model from WhissleAI. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for nemo. The card lists the license as cc-by-4.0.
This speech tagger performs transcription for 5 Indian Languages: Hindi, Punjabi, Marathi, Bengali and Gujarati. It annotates key entities, predicts speaker age, dialect and intent.
All-time downloads
329
Public
Repo size
465 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.nemo465 MB · 100%
At a glance
- Library
- nemo
- License
- cc-by-4.0
- Access
- Public
- Created
- Nov 8, 2024
- Updated
- Nov 8, 2024
- SHA
- 4b54d6a9
Base models
Model card
From the Hugging Face model README
Indo-Aryan Speech Tagger - Conformer CTC Model
This speech tagger performs transcription for 5 Indian Languages: Hindi, Punjabi, Marathi, Bengali and Gujarati. It annotates key entities, predicts speaker age, dialect and intent.
Model Details
- Model Type: NeMo ASR
- Architecture: Conformer CTC
- Language: Bengali, Hindi, Punjabi, Marathi, Gujarati
- Training Data: AI4Bharat IndicVoices Bengali V1 and V2 dataset
- Task: Speech Recognition with Entity Tagging
Usage
import nemo.collections.asr as nemo_asr
# Load model
asr_model = nemo_asr.models.EncDecCTCModel.from_pretrained('WhissleAI/speech-tagger_indo-aryan_ctc_meta')
# Transcribe audio
transcription = asr_model.transcribe(['path/to/audio.wav'])
print(transcription[0])
Model Training
- Base model: Conformer CTC
- Fine-tuned on AI4Bharat IndicVoices Marathi dataset
- Optimized for real-time transcription
License & Attribution
Please cite AI4Bharat when using this model: https://indicvoices.ai4bharat.org/
- Library
- nemo
- License
- cc-by-4.0
- Languages
- bn, hi, pa, mr, gu
- Created
- Nov 8, 2024
- Updated
- Nov 8, 2024