Downloads · 30 days
4
6% of all-time downloads
oron-tts-bucket
Maax-Bits/oron-tts-bucket
oron-tts-bucket is a text-to-speech model from Maax-Bits. Use it when you need text read aloud. It is set up for pytorch. The card lists the license as mit.
Non-autoregressive text-to-speech model based on F5-TTS (Flow Matching + Diffusion Transformer) for Mongolian (Khalkha Cyrillic) and Kazakh (Cyrillic).
All-time downloads
72
Public
Repo size
2.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.9 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jun 22, 2026
- Updated
- Jun 25, 2026
- SHA
- 37bc49c5
Try a prompt
Model card
From the Hugging Face model README
OronTTS — F5-TTS for Mongolian & Kazakh
Non-autoregressive text-to-speech model based on F5-TTS (Flow Matching + Diffusion Transformer) for Mongolian (Khalkha Cyrillic) and Kazakh (Cyrillic).
Model Details
| Parameter | Value |
|---|---|
| Architecture | F5-TTS (OT-CFM + DiT + Vocos) |
| dim | 512 |
| depth | 12 |
| heads | 8 |
| vocab_size | 65 |
| sample_rate | 24000 Hz |
| mel_bins | 100 |
Usage
from src.models.f5tts import F5TTS
from src.utils.checkpoint import CheckpointManager
model = F5TTS.from_config(config)
cm = CheckpointManager("checkpoints")
cm.load(model, path="f5tts_best.pt", device="cuda")
wav = model.synthesize(
text="Сайн байна уу",
lang="mn",
ref_audio_path="ref.wav",
)
Training
Trained on btsee/mbspeech_mn (3,846 Mongolian speech samples).
License
MIT
- Task
- Text-to-Speech
- Library
- pytorch
- License
- mit
- Languages
- mn, kk
- Created
- Jun 22, 2026
- Updated
- Jun 25, 2026