Downloads · 30 days
97
29% of all-time downloads
mongolian-vits-tts
Bokhbat/mongolian-vits-tts
mongolian-vits-tts is a text-to-speech model from Bokhbat. Use it when you need text read aloud. It is set up for coqui. The card lists the license as apache-2.0.
Multi-speaker VITS text-to-speech model for Mongolian, trained with Coqui TTS.
All-time downloads
330
Public
Repo size
1.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth1 GB · 93%
At a glance
- Task
- Text-to-Speech
- Library
- coqui
- License
- apache-2.0
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 19, 2026
- SHA
- 61ec0fb0
Try a prompt
Model card
From the Hugging Face model README
Mongolian VITS TTS
Multi-speaker VITS text-to-speech model for Mongolian, trained with Coqui TTS.
- Architecture: VITS (end-to-end, multi-speaker)
- Language: Mongolian (
mn) - Sample rate: 22050 Hz
- Speakers: 78 (see
speakers.pth) - Checkpoint: best model at training step 241549
Files
| File | Description |
|---|---|
best_model.pth | Best VITS checkpoint (eval loss) |
config.json | Coqui TTS training/inference config |
speakers.pth | Speaker manager / speaker id map |
tensorboard/ | TensorBoard event files (training curves) |
Usage
from huggingface_hub import hf_hub_download
from TTS.utils.synthesizer import Synthesizer
repo = "Bokhbat/mongolian-vits-tts"
model_path = hf_hub_download(repo, "best_model.pth")
config_path = hf_hub_download(repo, "config.json")
speakers_path = hf_hub_download(repo, "speakers.pth")
synth = Synthesizer(model_path, config_path, speakers_path, use_cuda=False)
wav = synth.tts("Сайн байна уу?", speaker_name=synth.tts_model.speaker_manager.speaker_names[0])
synth.save_wav(wav, "out.wav")
Training metrics
TensorBoard logs are included under tensorboard/ and render in the
Training metrics tab of this repository.
- Task
- Text-to-Speech
- Library
- coqui
- License
- apache-2.0
- Languages
- mn
- Created
- May 19, 2026
- Updated
- May 19, 2026