Indian Flag
Government Of India
A-
A
A+
UpvoteUpvote
0

AI4Bharat - Bengali IndicWav2Vec Speech Model

IndicWav2Vec is a multilingual speech model pre-trained on 40 Indian languages and fine-tuned for Automatic Speech Recognition (ASR) in 9 languages, achieving state-of-the-art results on multiple benchmarks.
  • Upvotes0upvotes
  • Downloads5downloads
  • Views608views
  • File size0
  • Shares0Shares
  • Last updatedupdated 18 Jul 2025
UpvoteUpvote
0
LICENSE MIT
SECTOR Sector Agnostic

About Model

IndicWav2Vec is a multilingual speech model pretrained on 40 Indian langauges. This model represents the largest diversity of Indian languages in the pool of multilingual speech models. The model is fine-tuned for downstream ASR for 9 languages and obtain state-of-the-art results on 3 public benchmarks, namely MUCS, MSR and OpenSLR. This model is fine tuned for Bengali Language.

Metadata Metadata

MIT

Sector Agnostic

Tahir Javed, Sumanth Doddapaneni, Abhigyan Raman, Kaushal Santosh Bhogale, Gowtham Ramesh, Anoop Kunchukuttan, Pratyush Kumar, Mitesh M. Khapra

N.A.

AI4Bharat

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

Open

21/02/25 13:20:45

N.A.

0

Tags

  • AI4Bharat
  • ASR
  • Deep Learning
  • Speech Recognition
  • IndicWav2Vec

Related Models Related Models

spk cond tts pflow Hindi
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Hindi.
BHARATGEN
  • See Upvoters0
  • Downloads3
  • Views126
  • File Size3.46 GB

spk cond tts pflow Marathi
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Marathi.
BHARATGEN
  • See Upvoters0
  • Downloads0
  • Views500
  • File Size3.49 GB

spk cond tts pflow Telugu
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Telugu.
BHARATGEN
  • See Upvoters0
  • Downloads0
  • Views85
  • File Size3.38 GB

spk cond tts pflow Bengali
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Bengali.
BHARATGEN
  • See Upvoters0
  • Downloads1
  • Views83
  • File Size3.49 GB

spk cond tts pflow Tamil
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Tamil.
BHARATGEN
  • See Upvoters0
  • Downloads4
  • Views139
  • File Size3.47 GB

Tamil vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Tamil.
BHARATGEN
  • See Upvoters0
  • Downloads2
  • Views550
  • File Size3.17 GB

Marathi vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Marathi.
BHARATGEN
  • See Upvoters0
  • Downloads2
  • Views508
  • File Size3.18 GB

Hindi vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Hindi.
BHARATGEN
  • See Upvoters0
  • Downloads4
  • Views1,080
  • File Size3.18 GB

Telugu vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Telugu.
BHARATGEN
  • See Upvoters0
  • Downloads2
  • Views490
  • File Size3.17 GB

Bengali vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Bengali.
BHARATGEN
  • See Upvoters0
  • Downloads1
  • Views319
  • File Size3.17 GB


Related Models by Organization Related Models by Organization

AI4Bharat - MultiIndic WikiBio Structured Summarization Model
MultiIndicWikiBioSS is a multilingual sequence-to-sequence model fine-tuned on the IndicWikiBio dataset for nine Indian languages
AI4BHARAT
  • See Upvoters0
  • Downloads5
  • Views148
  • File Size0

AI4Bharat- Hercules Bengali LORA: Evaluation Model
Hercule is a cross-lingual evaluation model from the CIA Suite, fine-tuned on the INTEL dataset to assess multilingual LLMs, particularly for Bengali
AI4BHARAT
  • See Upvoters0
  • Downloads9
  • Views335
  • File Size0

AI4Bharat- Hercules Hindi LORA: Evaluation Model
Hercule is a cross-lingual evaluation model from the CIA Suite designed to assess multilingual Large Language Models (LLMs) in Hindi
AI4BHARAT
  • See Upvoters0
  • Downloads24
  • Views535
  • File Size0

AI4Bharat - IndicBART Model for Structured Summarization
IndicBARTSS is a multilingual, sequence-to-sequence pre-trained model designed for natural language generation tasks in 11 Indic languages
AI4BHARAT
  • See Upvoters0
  • Downloads25
  • Views733
  • File Size0

AI4Bharat- LLaMA Prometheus Model
Llama-Prometheus is an English evaluation model from the CIA Suite, fine-tuned on the Feedback-Collection dataset using Llama-3.1-8B-Instruct
AI4BHARAT
  • See Upvoters0
  • Downloads10
  • Views436
  • File Size0

AI4Bharat- Hercules Telugu LORA: Evaluation Model
Hercule is a cross-lingual evaluation model from the CIA Suite, fine-tuned on the INTEL dataset to assess multilingual LLMs using English reference responses
AI4BHARAT
  • See Upvoters0
  • Downloads25
  • Views349
  • File Size0

AI4Bharat- Hercules Urdu LORA Model: Evaluation Model
Hercule is a cross-lingual evaluation model from the CIA Suite, fine-tuned on the INTEL dataset to assess multilingual LLMs using English references
AI4BHARAT
  • See Upvoters0
  • Downloads1
  • Views197
  • File Size0

AI4Bharat-IndicConformer-STT-PA-Hybrid-CTC-RNNT-Large (Punjabi): Automatic Speech Recognition Model
A large-scale Automatic Speech Recognition Model (ASR) model for Punjabi, utilizing a hybrid CTC-RNNT decoder.
AI4BHARAT
  • See Upvoters0
  • Downloads16
  • Views670
  • File Size0

AI4Bharat-IndicConformer-STT-ML-Hybrid-CTC-RNNT-Large (Malayalam): Automatic Speech Recognition Model
A large-scale Automatic Speech Recognition (ASR) model for Malayalam, utilizing a hybrid CTC-RNNT decoder
AI4BHARAT
  • See Upvoters0
  • Downloads39
  • Views851
  • File Size0

AI4Bharat-IndicConformer-STT-MNI-Hybrid-CTC-RNNT-Large (Manipuri): Automatic Speech Recognition Model
A large-scale Automatic Speech Recognition (ASR) model for Manipuri, utilizing a hybrid CTC-RNNT decoder
AI4BHARAT
  • See Upvoters0
  • Downloads19
  • Views714
  • File Size0


Related Models by Sector Related Models by Sector

spk cond tts pflow Hindi
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Hindi.
BHARATGEN
  • See Upvoters0
  • Downloads3
  • Views126
  • File Size3.46 GB

spk cond tts pflow Marathi
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Marathi.
BHARATGEN
  • See Upvoters0
  • Downloads0
  • Views500
  • File Size3.49 GB

spk cond tts pflow Telugu
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Telugu.
BHARATGEN
  • See Upvoters0
  • Downloads0
  • Views85
  • File Size3.38 GB

spk cond tts pflow Bengali
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Bengali.
BHARATGEN
  • See Upvoters0
  • Downloads1
  • Views83
  • File Size3.49 GB

spk cond tts pflow Tamil
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Tamil.
BHARATGEN
  • See Upvoters0
  • Downloads4
  • Views139
  • File Size3.47 GB

Tamil vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Tamil.
BHARATGEN
  • See Upvoters0
  • Downloads2
  • Views550
  • File Size3.17 GB

Marathi vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Marathi.
BHARATGEN
  • See Upvoters0
  • Downloads2
  • Views508
  • File Size3.18 GB

Hindi vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Hindi.
BHARATGEN
  • See Upvoters0
  • Downloads4
  • Views1,080
  • File Size3.18 GB

Telugu vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Telugu.
BHARATGEN
  • See Upvoters0
  • Downloads2
  • Views490
  • File Size3.17 GB

Bengali vb
This 150 M-parameter non-autoregressive speech generative model, developed by BharatGen, is designed for speaker-conditioned Text-to-speech in Bengali.
BHARATGEN
  • See Upvoters0
  • Downloads1
  • Views319
  • File Size3.17 GB


Related Models by Task Type Related Models by Task Type

Dhwani - Multilingual Speech LLM
Dhwani is India's first end-to-end trained speech Large Language Model (LLM), capable of directly understanding speech without a separate ASR (Automatic Speech Recognition) model, avoiding cascading ASR errors. It supports speech-to-text translation across multiple Indic languages and English.
OLA KRUTRIM
  • See Upvoters0
  • Downloads164
  • Views4,354
  • File Size0

AI4Bharat- IndicConformerAutomatic Speech Recognition (ASR) Model for Dogri
The Dogri ASR (Automatic Speech Recognition) model transcribes 16kHz mono-channel audio into text. It is based on a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder, ensuring accurate and efficient speech-to-text conversion
AI4BHARAT
  • See Upvoters0
  • Downloads14
  • Views631
  • File Size0

AI4Bharat- Maithili - IndicConformer Automatic Speech Recognition (ASR) Model
This model takes in mono-channel audio files at a 16,000 Hz sampling rate (WAV format) and outputs the transcribed text of the speech contained in the audio.
AI4BHARAT
  • See Upvoters0
  • Downloads29
  • Views912
  • File Size0

AI4Bharat- Konkani - IndicConformer Automatic Speech Recognition (ASR) Model
Automatic Speech Recognition (ASR) model for Konkani speech recognition, processing 16,000 KHz mono WAV audio and transcribing spoken content into text
AI4BHARAT
  • See Upvoters0
  • Downloads38
  • Views951
  • File Size0

AI4Bharat- Kashmiri - IndicConformer Automatic Speech Recognition (ASR) Model
This Automatic Speech Recognition (ASR) model transcribes Kashmiri speech from 16,000 KHz mono WAV audio files into text
AI4BHARAT
  • See Upvoters0
  • Downloads29
  • Views1,052
  • File Size0

AI4Bharat- Kannada - IndicConformer Automatic Speech Recognition (ASR) Model
This Kannada Automatic Speech Recognition (ASR) model transcribes 16kHz mono-channel audio into text. It utilizes a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder for high-accuracy speech recognition.
AI4BHARAT
  • See Upvoters0
  • Downloads27
  • Views1,062
  • File Size0

AI4Bharat- Hindi - IndicConformer Automatic Speech Recognition (ASR) Model
This Hindi Automatic Speech Recognition (ASR) model converts 16kHz mono-channel audio into text. It is based on a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder, ensuring high-accuracy speech transcription.
AI4BHARAT
  • See Upvoters0
  • Downloads105
  • Views2,794
  • File Size0

AI4Bharat- Gujarati - IndicConformer Automatic Speech Recognition (ASR) Model
This Gujarati Automatic Speech Recognition (ASR) model converts 16kHz mono-channel audio into text. Built on a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder, it delivers high-accuracy speech-to-text transcription.
AI4BHARAT
  • See Upvoters0
  • Downloads42
  • Views638
  • File Size0

AI4Bharat - Telugu IndicWav2Vec Speech Model
IndicWav2Vec is a multilingual speech model pre-trained on 40 Indian languages and fine-tuned for Automatic Speech Recognition (ASR) in 9 languages, achieving state-of-the-art results on multiple benchmarks.
AI4BHARAT
  • See Upvoters0
  • Downloads51
  • Views1,400
  • File Size0

AI4Bharat- Bodo - IndicConformer Automatic Speech Recognition (ASR) Model
The Bodo ASR (Automatic Speech Recognition) model converts 16kHz mono-channel audio into text. Built on a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder, it ensures high-accuracy speech-to-text transcription.
AI4BHARAT
  • See Upvoters0
  • Downloads36
  • Views1,017
  • File Size0