asiff00/Training-TTS

Train and finutune text-to-speech models for Bengali and many other languages!

18

stars

11

commits

Jupyter Notebook

primary language

Apr 2, 2025

updated

audio-processing

finetune

kokoro-tts

speech-synthesis

styletts2

text-to-speech

tts

xttsv2

README

Training TTS

This is a repository to train TTS models. All the training/finetuning are focusing on Bengali language here but can be used for any languages with minimal changes. The most confusing part is the data formatting; once you get it right for the dataset in hand, the rest just becomes easier. I'll be posting more about it gradually. I will also improve the other parts of the repo as well.

Trained/Finetuned Models

Bangla TTS contains a list of models trained/tuned using scripts from this repository. Model that we have added to the collections so far are:

References

Contributors

11 commits

Similar repos

Aratako/T5Gemma-TTS

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

312

HoseinAzad/SpeechT5-Non-English-TTS

Fine-tune SpeechT5 for non-English text-to-speech task, implemented in PyTorch.

8

gokhaneraslan/chatterbox-finetuning

Fine-tuning toolkit for Chatterbox TTS & Chatterbox TURBO models. Supports 23 languages with smart…

109

franciscocarloserra/ttslibre

Small, fast, free: an open recipe for a sub-100M TTS. Code, data, weights.

4

sbintuitions/sarashina2.2-tts

73

maum-ai/univnet

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

286

Aratako/Irodori-TTS

A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

1,244

jik876/hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

2,368

Languages

Jupyter Notebook

97.6%

Python

2.4%

asiff00/Training-TTS

Train and finutune text-to-speech models for Bengali and many other languages!

18

stars

11

commits

Jupyter Notebook

primary language

Apr 2, 2025

updated

audio-processing

finetune

kokoro-tts

speech-synthesis

styletts2

text-to-speech

tts

xttsv2

README

Training TTS

This is a repository to train TTS models. All the training/finetuning are focusing on Bengali language here but can be used for any languages with minimal changes. The most confusing part is the data formatting; once you get it right for the dataset in hand, the rest just becomes easier. I'll be posting more about it gradually. I will also improve the other parts of the repo as well.

Trained/Finetuned Models

Bangla TTS contains a list of models trained/tuned using scripts from this repository. Model that we have added to the collections so far are:

References

Similar repos

Aratako/T5Gemma-TTS

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

312

HoseinAzad/SpeechT5-Non-English-TTS

Fine-tune SpeechT5 for non-English text-to-speech task, implemented in PyTorch.

8

gokhaneraslan/chatterbox-finetuning

Fine-tuning toolkit for Chatterbox TTS & Chatterbox TURBO models. Supports 23 languages with smart…

109

franciscocarloserra/ttslibre

Small, fast, free: an open recipe for a sub-100M TTS. Code, data, weights.

4

sbintuitions/sarashina2.2-tts

73

maum-ai/univnet

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

286

Aratako/Irodori-TTS

A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

1,244

jik876/hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

2,368

Contributors

11 commits

Languages

Jupyter Notebook

97.6%

Python

2.4%