Government Of India
A-
A
A+
SPRING LAB PUNJABI-STREAMING
Automatic Speech Recognition (ASR) model for Punjabi speech recognition, processing audio and transcribing spoken content into text.
About Model
Automatic Speech Recognition (ASR) model for Punjabi speech recognition, developed using the Icefall toolkit with the Zipformer architecture. The model is trained on the Punjabi dataset, which consists of approximately 400 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 PUNJABI-STREAMING
Metadata
Attribution 4.0 International (CC BY- 4.0)
SPRING LAB IITM
Speech -to-text Conversion
PyTorch
Open
Science, Technology and Research
09/01/26 06:31:40
260.42 MB
jit_script_chunk_32_left_128.pt ( 260.40 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
4 
260.42 MB 
190
Tags
- ASR
- Pytorch
- IITM
- spring_lab
- Punjab
- streaming
- MODELS
- zipformer
- Icefall-K2
License Control
Attribution 4.0 International (CC BY- 4.0)
Version Control
Version 1(260.42 MB)
- admin·6 month(s) ago
jit_script_chunk_32_left_128.pt
tokens.txt
More Models from Digital India BHASHINI Division
SPRING-INX-DATA2VEC-AQC-GUJARATI
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
ssl
Low-resource languages
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
gujarati
- 0
- 1
- 3.52 GB
6
Updated Today
SPRING-INX-DATA2VEC-AQC-HINDI
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 languages
ssl
IITM
spring_lab
Data2vec_aqc
SSL_finetunning
hindi
- 0
- 0
- 3.53 GB
- 8
Updated Today
SPRING-INX-DATA2VEC-AQC-MANIPURI
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
Manipuri
Low Resource Languages
SSL_finetunning
Data2vec_aqc
spring_lab
IITM
ssl
- 0
- 0
- 3.52 GB
- 8
Updated Today
SPRING-INX-DATA2VEC-AQC-ASSAMESE
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
SSL_finetunning
Assamese
ssl
IITM
spring_lab
Data2vec_aqc
Low-resource languages
- 0
- 0
- 3.52 GB
- 5
Updated Today
IndicXlit
A Transformer-based multilingual transliteration model
NLP
Language Modeling
Multilingual Translation
Machine Translation
Regional Languages
Indian Languages
transliteration
- 0
- 49
- 3.94 MB
- 1,181
Updated 10 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.
Indian Languages
Computational Linguistics
NLP
Indic-TransV2
Regional Languages
Machine Translation
Multilingual Translation
Bilingual Translation
Language Modeling
Machine Translation
- 1
- 88
- 214.60 KB
- 2,308
Updated 10 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.
Transformer
Text to Speech
Language Detection
Multilingual
NLP
Text Processing
- 0
- 101
- 286.72 MB
- 1,854
Updated 10 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
NLP
Foreigners
Multilingual
Transformer
Token Classification
Pytorch
Samanantar
Bert
NER
- 2
- 145
- 591.28 MB
- 2,723
Updated 10 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)
NLP
Text Processing
Deep Learning
Transformer
Text Language Detection
Multilingual
AI4Bharat
Bhashini
- 5
- 272
- 3 MB
- 5,158
Updated 10 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
- 199
Updated 15 day(s) ago
© 2026 - Copyright AIKosh. All rights reserved.