Government Of India
A-
A
A+
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.
.png){kind=small}
About Model
Our speaker-conditioned Text-to-speech model is a non-autoregressive speech generative model designed for Indian languages, consisting of two key components: an audio model and an enhanced duration predictor. Together, these components comprise approximately 150 million parameters. The audio model is based on continuous normalizing flows (CNFs) and transforms a simple distribution into a complex conditional audio distribution, p(missing audio, speaker audio, text), using a neural network trained with flow-matching via vector field regression. To better handle the prosodic richness of Indian languages, we extend the standard duration predictor architecture. Unlike Voicebox, which uses only text and durations, our model incorporates a 3-second speaker prompt along with the text. This enables the duration predictor to extract speaker-specific prosodic cues from the reference audio, resulting in more accurate and natural duration estimates.
The model is trained from scratch on publicly available Indian language datasets and is optimized for speech infilling tasks such as continuous sentence completion and cross-sentence completion. Architectural modifications were made throughout to adapt the system for the diverse phonetic, rhythmic, and intonational patterns of Indian languages.
For any queries, please visit https://bharatgen.discourse.group/invites/BcouFsKk4g
For any queries, please visit https://bharatgen.discourse.group/invites/BcouFsKk4g
spk cond tts pflow Hindi
Metadata
MIT
BharatGen
Text-to-Speech Model
PyTorch
Restricted
Sector Agnostic
29/04/25 06:54:27
N.A
3.46 GB
Hindi ( 5 files, 1 directories )
pipeline2_v2_api
22 files, 10 directories
checkpoint_1930.pt
1.15 GB
checkpoint_20200.pt
969.10 MB
infer.sh
5.98 KB
readme.txt
228 Bytes
requirements.txt
4.45 KB
Activity Overview
0
3 
3.46 GB 
81
Tags
- TextToSpeech
License Control
MIT
Version Control
Version 1(3.46 GB)
- admin·1 year(s) ago
- chevron_right
Hindi
- chevron_right
pipeline2_v2_api
checkpoint_1930.pt
checkpoint_20200.pt
infer.sh
readme.txt
requirements.txt
More Models from null
Shrutam-2
Shrutam-2 is a LLM based automatic speech recognition system for 12 major Indian languages. It bridges a Conformer speech encoder with a pretrained LLM decoder through a Mixture-of-Experts (MoE) projection layer, enabling high-quality, prompt-controllable transcription across diverse Indic languages.
Automatic Speech Recognition
Speech-to-Text
- 0
- 0
- 8.37 GB
23
Updated 5 day(s) ago
BHARATGEN
Param-1-5B
Param-1-5B is a bilingual (English–Hindi) large language model developed under the Param-1 family. With 5 billion parameters, this model extends the capabilities of Param-1-2.9B by incorporating enhanced mathematical reasoning and code understanding/generation.
The model is pretrained from scratch and designed to serve as a strong foundation for downstream tasks such as mathematical problem solving, and code-related understanding / generation.
Param-1-Instruct
BharatGen introduces the early checkpoint of SFT (Supervised Fine-Tuned) for Param 1, a bilingual language model trained from scratch in English and Hindi. With 2.9 billion parameters, this checkpoint builds upon the pretraining phase and serves as a foundation for more downstream tasks, safety testing, and customization.
BharatGen - Param 1 Indic-Scale Bilingual Foundation Model
Param1 is a 2.9 billion parameter language model pretrained on English and Hindi, designed for text completion.
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
pretrained
Mixture of Experts
- 1
- 45
- 57.29 GB
- 1,191
Updated 2 month(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.
multilingual-TTS
Text-to-Speech
Multilingual Speech
Audio Synthesis
sooktam2
- 0
- 9
- 1.25 GB
- 892
Updated 2 month(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.
BharatGen-AgriParam
Large language model fine-tuned from Param-1-2.9B-Instruct on a high-quality, India-centric agriculture dataset.
BharatGen-FinanceParam
large language model fine-tuned from Param-1-2.9B-Instruct on a high-quality finance dataset.
BharatGen-LegalParam
Large language model fine-tuned from Param-1-2.9B-Instruct on an exhaustive India-centric legal dataset.
© 2026 - Copyright AIKosh. All rights reserved.