Downloads · 30 days
342
17% of all-time downloads
EMTIAZZ/bangladeshi-bangla-tts-vits
bangladeshi-bangla-tts-vits is a text-to-speech model from EMTIAZZ. Use it when you need text read aloud. The card lists the license as apache-2.0.
A Text-to-Speech model for Bangladeshi Bangla (Bengali) built using the VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) architecture. Trained to capture authentic Bangladeshi pronu…
Downloads · 30 days
342
17% of all-time downloads
All-time downloads
2K
Public
Repo size
998 MB
Likes
7
Public
Click a slice to open those files.
.pth998 MB · 100%
From the Hugging Face model README
A Text-to-Speech model for Bangladeshi Bangla (Bengali) built using the VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) architecture. Trained to capture authentic Bangladeshi pronunciation and accent patterns.
| Property | Value |
|---|---|
| Architecture | VITS (end-to-end TTS) |
| Language | Bangla (bn) |
| Focus | Bangladeshi pronunciation & accent |
| License | Apache 2.0 |
VITS (Kim et al., 2021) is an end-to-end TTS model that:
Bangla is spoken by 230M+ people worldwide, making it the 7th most spoken language globally. Yet, high-quality, publicly available Bangla TTS models remain scarce. This model is part of an effort to bridge that gap for the Bangladeshi speech community.
For production-quality Bangla TTS, see the Orpheus 3B fine-tuned models which use a much larger LLM backbone:
| Model | Scale | Quality |
|---|---|---|
| This model | VITS | Good |
| orpheus-3b-bangla-high-data | Orpheus 3B (99K samples) | Best |
| orpheus-3b-bangla-small-data | Orpheus 3B (39K samples) | Better |
Training code and data pipeline available at: github.com/EMTIAZ-RUET/bangladeshi-bangla-tts-finetuning
@misc{emtiaz2025banglavirus,
author = {Emtiaz Uddin Ahmed},
title = {Bangladeshi Bangla TTS — VITS},
year = {2025},
url = {https://huggingface.co/EMTIAZZ/bangladeshi-bangla-tts-vits}
}
Emtiaz Uddin Ahmed — AI/ML Engineer at Markopolo.ai, Dhaka, Bangladesh. GitHub · Portfolio