Government Of India
A-
A
A+
SPRING LAB BENGALI-STREAMING
Automatic Speech Recognition (ASR) model for BENGALI speech recognition, processing audio and transcribing spoken content into text.
About Model
Automatic Speech Recognition (ASR) model for BENGALI speech recognition, developed using the Icefall toolkit with the Zipformer architecture. The model is trained on a dataset consisting of approximately 750 hours of labelled speech. It is trained on 16 kHz audio, including naturally occurring code-mixed speech, enabling robust recognition of bilingual Indian speech patterns. The system is based on a 65M-parameter Zipformer-Medium encoder, paired with an RNN-T prediction network and joiner, forming a low-latency streaming ASR model with 16 encoder layers and a 512-dimensional representation.
SPRING LAB BENGALI-STREAMING
Metadata
Attribution 4.0 International (CC BY- 4.0)
SPRING LAB IITM
Speech -to-text Conversion
PyTorch
Open
Science, Technology and Research
12/12/25 05:55:37
268.26 MB
jit_script_chunk_32_left_128.pt ( 268.23 MB )
To preview this file, you need to be a registered user. Please complete the registration process to gain access and continue viewing the content.
Activity Overview
0
0 
268.26 MB 
219
Tags
- ASR
- models
- IITM
- spring_lab
- streaming
- zipformer
- Icefall-K2
License Control
Attribution 4.0 International (CC BY- 4.0)
Version Control
Version 1(268.26 MB)
- admin·7 month(s) ago
jit_script_chunk_32_left_128.pt
tokens.txt
More Models from Digital India BHASHINI Division
IndicXlit
A Transformer-based multilingual transliteration model
Indian Languages
transliteration
Regional Languages
Machine Translation
Multilingual Translation
Language Modeling
NLP
- 0
- 49
- 3.94 MB
1,157
Updated 6 day(s) ago
Indic Trans2
AI4Bharat's Indic-Trans-v2 is a multilingual Transformer (~1.1BM) NMT model trained on Samanantar v2 dataset which is the largest publicly available parallel corpora collection for languages of India at the time of writing (23 March 2023). We currently release two models - Indic to English and English to Indic and support all the 22 scheduled languages of India.
Machine Translation
Computational Linguistics
Indian Languages
Indic-TransV2
NLP
Regional Languages
Machine Translation
Multilingual Translation
Bilingual Translation
Language Modeling
- 1
- 85
- 214.60 KB
- 2,252
Updated 6 day(s) ago
Bhashini - Fastspeech2 Model using (HS)
Text-to-speech models trained using FastPitch and HiFi-GAN vocoder, separately for each language. Supports both 'female' and 'male' voices.
Text to Speech
Multilingual
Language Detection
Transformer
Text Processing
NLP
- 0
- 99
- 286.72 MB
- 1,828
Updated 6 day(s) ago
Bhashini - IndicNER
IndicNER is a multilingual Named Entity Recognition model fine-tuned on 11 Indian languages to identify named entities in text
Bert
Samanantar
Pytorch
Token Classification
Transformer
NLP
Foreigners
Multilingual
NER
- 2
- 142
- 591.28 MB
- 2,690
Updated 6 day(s) ago
Bhashini-AI4Bharat Textual Language Detection v1.0
Detect language from provided text, Currently supports 23 languages (English, Bangla, Manipuri, Bodo, Konkani, Oriya, Nepali, Marathi, Sindhi, Sanskrit, Malayalam, Urdu, Assamese, Telugu, Dogri, Gujarati, Kashmiri, Punjabi, Santali, Maithili, Hindi, Tamil, Kannada)
Bhashini
Text Language Detection
Transformer
Deep Learning
Text Processing
NLP
AI4Bharat
Multilingual
- 5
- 270
- 3 MB
- 5,100
Updated 6 day(s) ago
SPRING-INX-DATA2VEC-AQC-SANSKRIT
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.
The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
low-resource-language
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
ssl
Sanskrit
- 0
- 5
- 3.52 GB
- 197
Updated 11 day(s) ago
SPRING-INX-DATA2VEC-AQC-PUNJABI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.
The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
low-resource-language
SSL_finetunning
Data2vec_aqc
PUNJABI
spring_lab
IITM
ssl
- 0
- 3
- 3.52 GB
- 189
Updated 11 day(s) ago
SPRING-INX-DATA2VEC-AQC-ODIA
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.
The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
low-resource-language
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
ssl
Odia
- 0
- 5
- 3.52 GB
- 161
Updated 11 day(s) ago
SPRING-INX-DATA2VEC-AQC-MALAYALAM
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.
The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
low-resource-language
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
malayalam
ssl
- 0
- 5
- 3.52 GB
- 205
Updated 11 day(s) ago
SPRING-INX-DATA2VEC-AQC-MARATHI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.
The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
low-resource-language
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
ssl
Marathi
- 0
- 6
- 3.52 GB
- 152
Updated 11 day(s) ago
© 2026 - Copyright AIKosh. All rights reserved.