Government Of India
A-
A
A+
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.
0 
93 
286.72 MB 
1,755
Model Card
Run Model
About Model
This repository contains a Fastspeech2 Model for 16 Indian languages (male and female both) implemented using the Hybrid Segmentation (HS) for speech synthesis. The model is capable of generating mel-spectrograms from text inputs and can be used to synthesize speech.
Fs2 is composed of 6 feed-forward Transformer blocks with multi-head self-attention and 1D convolution on both phoneme encoder and mel-spectrogram decoder. In each feed-forward Transformer, the hidden size of multi-head attention is set to 256 and the number of head is set to 2. The kernel size of 1D convolution in the two-layer convolution network is set to 9 and 1, and the input/output size of the number of channels in the first and the second layer is 256/1024 and 1024/256. The duration predictor and variance adaptor, which are composed of stacks of several convolution networks and the final linear projection layer. The convolution layers of the duration predictor and variance adaptor are set to 2 and 5, the kernel size is set to 3, the input/output size of all layers is 256/256, and the dropout rate is set to 0.5.
Bhashini - Fastspeech2 Model using (HS)
Metadata
MIT
SMT Lab IIT Madras
Speech Synthesis (TTS) Model
Other
Open
Sector Agnostic
06/07/26 16:10:49
286.72 MB
Tags
- Multilingual
- NLP
- Text Processing
- Transformer
- Text to Speech
- Language Detection
assamese ( 2 directories )
female
1 directories
male
1 directories
License Control
MIT
Version Control
Version 2(286.72 MB)
- admin·1 year(s) ago
- chevron_right
assamese
- chevron_right
female
- chevron_right
male
- chevron_right
bengali
- chevron_right
bodo
- chevron_right
charmap
- chevron_right
english
.gitattributes
api.py
app.py
environment.yml
get_phone_mapped_python.py
- more_horiz 25 more
Version 1(7.06 KB)
- admin·1 year(s) ago
No File(s) Found!
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
- 46
- 3.94 MB
- 1,111
Updated 1 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
- 0
- 84
- 214.60 KB
- 2,154
Updated 1 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
- 93
- 286.72 MB
- 1,755
Updated 1 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
- 133
- 591.28 MB
- 2,648
Updated 1 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
- 4
- 266
- 3 MB
- 5,014
Updated 1 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
- 193
Updated 6 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
- 186
Updated 6 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
- 4
- 3.52 GB
- 156
Updated 6 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
- 202
Updated 6 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
- 148
Updated 6 day(s) ago
© 2026 - Copyright AIKosh. All rights reserved.