Indian Flag
Government Of India
A-
A
A+
UpvoteUpvote
0

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.
  • Upvotes0upvotes
  • Downloads141downloads
  • Views2,777views
  • File size0
  • Shares1Shares
  • Last updatedupdated 06 Jul 2026
UpvoteUpvote
0
LICENSE MIT
SECTOR Sector Agnostic

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.

Metadata Metadata

MIT

Sector Agnostic

SMT Lab IIT Madras

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

Open

06/07/26 16:10:49

N.A.

286.72 MB

Tags Tags

  • Multilingual
  • NLP
  • Text Processing
  • Transformer
  • Text to Speech
  • Language Detection

assamese ( 2 directories )


Directory
female

1 directories

Directory
male

1 directories

License Control License Control

MIT

Version Control Version Control

FolderVersion 2(286.72 MB)
  • admin·1 year(s) ago
    • chevron_rightFolder
      assamese
      • chevron_rightFolder
        female
      • chevron_rightFolder
        male
    • chevron_rightFolder
      bengali
    • chevron_rightFolder
      bodo
    • chevron_rightFolder
      charmap
    • chevron_rightFolder
      english
    • undefined
      .gitattributes
    • undefined
      api.py
    • undefined
      app.py
    • undefined
      environment.yml
    • undefined
      get_phone_mapped_python.py
    • more_horiz 25 more

More Models from Digital India BHASHINI Division More Models from Digital India BHASHINI Division

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters2
  • Downloads106
  • Views3,929
  • File Size64.91 KB

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views25
  • File Size2.66 GB

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views18
  • File Size4.65 GB

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size496.68 MB

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads8
  • Views62
  • File Size355.33 MB

IITG-Mizo-ASR-v1
A mizo ASR model.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads8
  • Views58
  • File Size5.75 GB

IITG-Mizo-MT-v1
A Machine Translation model for English-Mizo
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads13
  • Views58
  • File Size5.14 GB

COILD Multilingual Translation
COILD Multilingual Translation Model (COILD-Mul-MT)
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads0
  • Views36
  • File Size0

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads2
  • Views68
  • File Size1.18 GB

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.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters1
  • Downloads3
  • Views115
  • File Size0