Government Of India
A-
A
A+
ORGANISATION 
Upvote 0
SPRING-INX-DATA2VEC-AQC-KANNADA
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
- 0upvotes
7downloads
189views
3.52 GB
0Shares
updated 01 Jul 2026
Upvote 0
LICENSE Attribution 4.0 International (CC BY- 4.0)
SECTOR Science, Technology and Research
About Model
Data2vec-aqc is a self-supervised learning (SSL) model for speech representation learning, specifically designed to improve Automatic Speech Recognition (ASR) in low-resource settings. It is built using the Fairseq toolkit and extends the original data2vec framework by introducing three key modules: a quantizer (similar to wav2vec 2.0), a clustering module (from ccc-wav2vec 2.0), and a cross-contrastive loss mechanism. The model uses a Transformer-based architecture, consistent with data2vec, and operates in a teacher-student training setup. The student network processes randomly augmented versions of audio samples, while the teacher network (an exponentially moving average of the student) provides target representations. The student learns to predict the teacher’s contextualised latent representations, enabling robust feature learning.
Metadata
Attribution 4.0 International (CC BY- 4.0)
Science, Technology and Research
SPRING LAB IITM
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
Open
28/01/26 06:35:52
N.A.
3.52 GB
Tags
Related Models
Indic-Conformer model for ASR
Indo-Aryan Indic-Conformer is a multilingual speech model for North-Indian languages. This model is based on Conformer large architecture, with 115M parameters.
shuka-v1
Multilingual audio to text model
sarvam-1
India's first indic model, pretrained on 4 trillion tokens
LUCAN 10B
LUCAN 10B Physics MoE is an 11B parameter multi-domain scientific foundation model built on a hybrid Mamba2 state-space and 12-layer Sparse Mixture-of-Experts (MoE) architecture with a PhysicsConstrainedOutputHead. It models continuous scientific latents across fluid transport, chemical reactors, phase-change thermal physics, and molecular systems.
LUCAN 3B
LUCAN 3B is an approximately 3-billion-parameter scientific AI model from Shodh AI for processing numerical reactor data. This release includes the model weights, dedicated tokenizers and matching adapters for bioreactor and continuous-flow reactor applications, along with loading instructions and an introductory guide.
Joel-Speech-TTS
A Text-to-Speech (TTS) model developed for the Mizo language that converts written Mizo text into natural-sounding speech, supporting the development of Mizo-language voice applications and accessibility solutions.
mizo-f5-tts-v1
A Text-to-Speech (TTS) model developed for the Mizo language that converts written Mizo text into natural-sounding speech, supporting the development of Mizo-language voice applications and accessibility solutions.
MIZO MT
This Machine Translation (MT) model translates text from one language to another using a trained neural network. It can support multilingual communication and language translation applications. Translation quality depends on language coverage, training data, and contextual accuracy. For Mizo, evaluate the model using representative test sentences before deployment.
IITG-TTS-v1
The TTS was built using 5.18 hours of Mizo speech data. The Mizo text-to-speech (TTS) synthesis system built using the Variational Inference with Adversarial Learning for Text-to-Speech (VITS) framework.
IITG-Mizo-ASR-v1
A mizo ASR model.
Related Models by Organization
Indic-Conformer model for ASR
Indo-Aryan Indic-Conformer is a multilingual speech model for North-Indian languages. This model is based on Conformer large architecture, with 115M parameters.
Joel-Speech-TTS
A Text-to-Speech (TTS) model developed for the Mizo language that converts written Mizo text into natural-sounding speech, supporting the development of Mizo-language voice applications and accessibility solutions.
mizo-f5-tts-v1
A Text-to-Speech (TTS) model developed for the Mizo language that converts written Mizo text into natural-sounding speech, supporting the development of Mizo-language voice applications and accessibility solutions.
MIZO MT
This Machine Translation (MT) model translates text from one language to another using a trained neural network. It can support multilingual communication and language translation applications. Translation quality depends on language coverage, training data, and contextual accuracy. For Mizo, evaluate the model using representative test sentences before deployment.
IITG-TTS-v1
The TTS was built using 5.18 hours of Mizo speech data. The Mizo text-to-speech (TTS) synthesis system built using the Variational Inference with Adversarial Learning for Text-to-Speech (VITS) framework.
IITG-Mizo-ASR-v1
A mizo ASR model.
IITG-Mizo-MT-v1
A Machine Translation model for English-Mizo
COILD Multilingual Translation
COILD Multilingual Translation Model (COILD-Mul-MT)
Mizomade-Mizo-EN-NLLB-S1
Fine-tuned pre trained model for Mizo-English machine translation, trained on Mizo-English parallel datasets to improve translation performance for the Mizo language.
BHASHINI IISc Sourashtra VITS TTS Models
VITS text-to-speech models for Sourashtra, a low-resource Indo-Aryan language. There are male and female voices, and each voice accepts text in either Tamil script or Sourashtra script.
Related Models by Sector
shuka-v1
Multilingual audio to text model
sarvam-1
India's first indic model, pretrained on 4 trillion tokens
LUCAN 10B
LUCAN 10B Physics MoE is an 11B parameter multi-domain scientific foundation model built on a hybrid Mamba2 state-space and 12-layer Sparse Mixture-of-Experts (MoE) architecture with a PhysicsConstrainedOutputHead. It models continuous scientific latents across fluid transport, chemical reactors, phase-change thermal physics, and molecular systems.
LUCAN 3B
LUCAN 3B is an approximately 3-billion-parameter scientific AI model from Shodh AI for processing numerical reactor data. This release includes the model weights, dedicated tokenizers and matching adapters for bioreactor and continuous-flow reactor applications, along with loading instructions and an introductory guide.
MIZO MT
This Machine Translation (MT) model translates text from one language to another using a trained neural network. It can support multilingual communication and language translation applications. Translation quality depends on language coverage, training data, and contextual accuracy. For Mizo, evaluate the model using representative test sentences before deployment.
COILD Multilingual Translation
COILD Multilingual Translation Model (COILD-Mul-MT)
GNM Generative aNthropometric Model - v3
GNM (pronounced genome) is a state-of-the-art parametric 3D statistical model of the human head developed by Google. Learned from a large dataset of high-resolution 3D scans, GNM provides fine-grained, disentangled control over facial identity, expressions, and head pose, complete with controllable internal anatomy (eyeballs, teeth, and tongue).
The model is released under the Apache 2.0 permissive license, suitable for both academic research and commercial applications.
BHASHINI IISc Sourashtra VITS TTS Models
VITS text-to-speech models for Sourashtra, a low-resource Indo-Aryan language. There are male and female voices, and each voice accepts text in either Tamil script or Sourashtra script.
DiffusionGemma
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
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
Related Models by Task Type
NCERT-TUTOR-v3
NCERT-aligned tutor LoRA for on-device K-12 tutoring. Runs on 4 GB VRAM (RTX 3050).
Stage-3 chained adapter: 15.7k curated questions (Grades 6-12, 13 subjects) + 3 DPO stages
(math reasoning, mined factuality, multi-subject). 58% on held-out NCERT math with worked steps.
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
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
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
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
KisanSLM-Gemma3n-E2B-GGUF
This is a zipped GGUF. Download and unzip the file.
KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
KisanSLM-Llama3-2-1B-GGUF
This is a zipped GGUF. Download and unzip the file. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
KisanSLM-LMF2-5-1-2B-GGUF
This is a zipped GGUF. Download and unzip the file. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
KisanSLM-Qwen3-1-7b-GGUF
This is a zipped fine tune of Qwen3 1.7b model. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
KisanSLM
KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural settings.
© 2026 - Copyright AIKosh. All rights reserved.