Indian Flag
Government Of India
A-
A
A+

BharatGen - ASR: Hindi

This is a 30M-parameter hybrid CTC-RNNT Branchformer model designed for Automatic Speech Recognition (ASR) in the Hindi language.

About Model

This 30M-parameter hybrid CTC-RNNT Branchformer model, developed by BharatGen, is designed for Automatic Speech Recognition (ASR) in Hindi. Trained on over 1,000 hours of Hindi audio-text parallel data, the model achieves a Word Error Rate (WER) of 14.85% on the Vistaar benchmark, averaged across all included datasets.
For any queries, please visit https://bharatgen.discourse.group/invites/BcouFsKk4g

BharatGen - ASR: Hindi

Metadata Metadata

MIT

BharatGen

Automatic Speech Recognition Model

PyTorch

Restricted

BharatGen

Sector Agnostic

29/04/25 06:29:32

N.A

94.49 MB

Activity Overview Activity Overview

  • Downloads0
  • Downloads 5
  • Views 290
  • File Size 94.49 MB

Tags Tags

  • ASR
  • SpeechToText
  • AutomaticSpeechRecognition
  • Hindi
  • generative AI

License Control License Control

MIT

Version Control Version Control

FolderVersion 1(94.49 MB)
  • admin·11 month(s) ago
    • chevron_rightFolder
      file-1745413290994-780372815
      • chevron_rightFolder
        BharatGen-ASR

More Models from null More Models from null

Param2-17B-Thinking
BharatGen presents Param-2-17B-MoE-A2.4B, a large-scale Mixture-of-Experts (MoE) language model designed to deliver high model capacity while retaining the inference efficiency of a much smaller dense model. It uses a Hybrid MoE architecture with 17B total parameters, while activating only 2.4B parameters per token.
Multilingual Text
Mixture of Experts
pretrained
  • See Upvoters1
  • Downloads18
  • File Size25.33 GB
  • Views532
Updated 26 day(s) ago

BHARATGEN

BharatGen Multilingual TTS - Sooktam2
Sooktam-2 is a multilingual Indic Text-to-Speech model by BharatGen supporting 12 languages including Hindi, Marathi, Tamil, Telugu, Bengali, Urdu, Punjabi and Indian English. It enables high-quality speech synthesis with reference-guided voice conditioning, preserving speaker voice, accent and prosody for natural and expressive generation.
sooktam2
Audio Synthesis
Multilingual Speech
Text-to-Speech
multilingual-TTS
  • See Upvoters0
  • Downloads9
  • File Size1.25 GB
  • Views391
Updated 29 day(s) ago

BHARATGEN

BharatGen - Param-1-7B-MoE Advancing Multilingual GenAI for India
Param-1-7B-MoE is a multilingual large language model developed under the Param-1 family as part of BharatGen – A Suite of Generative AI Technologies for India. With 7 billion parameters and a Mixture of Experts (MoE) architecture, the model is designed to better understand and generate text across English, Hindi, and 14 additional Indian languages. The model is pretrained from scratch with a strong focus on linguistic diversity, cultural context, and large-scale multilingual representation.
region:us
safetensors
mixtral
  • See Upvoters1
  • Downloads75
  • File Size0
  • Views1,007
Updated 3 month(s) ago

BHARATGEN

A2TTS-Malayalam Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
multilingual-TTS
TextToSpeech
SpeechSynthesis
  • See Upvoters0
  • Downloads16
  • File Size1.62 GB
  • Views1,518
Updated 8 month(s) ago

BHARATGEN

A2TTS-Gujarati Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
multilingual-TTS
SpeechSynthesis
TextToSpeech
  • See Upvoters1
  • Downloads20
  • File Size1.62 GB
  • Views3,097
Updated 8 month(s) ago

BHARATGEN

A2TTS-Telugu Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
multilingual-TTS
TextToSpeech
SpeechSynthesis
  • See Upvoters0
  • Downloads21
  • File Size1.62 GB
  • Views1,765
Updated 8 month(s) ago

BHARATGEN

A2TTS-Tamil Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
SpeechSynthesis
TextToSpeech
multilingual-TTS
  • See Upvoters0
  • Downloads48
  • File Size1.62 GB
  • Views2,637
Updated 8 month(s) ago

BHARATGEN

A2TTS-Punjabi Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
multilingual-TTS
TextToSpeech
SpeechSynthesis
  • See Upvoters0
  • Downloads34
  • File Size1.62 GB
  • Views1,448
Updated 8 month(s) ago

BHARATGEN

A2TTS-Marathi Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
multilingual-TTS
TextToSpeech
SpeechSynthesis
  • See Upvoters2
  • Downloads22
  • File Size1.62 GB
  • Views2,822
Updated 8 month(s) ago

BHARATGEN

A2TTS-Kannada Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
multilingual-TTS
TextToSpeech
SpeechSynthesis
  • See Upvoters0
  • Downloads11
  • File Size1.62 GB
  • Views1,674
Updated 8 month(s) ago

BHARATGEN