Downloads · 30 days
63
12% of all-time downloads
f5-tts-hindhi
SwarajSolanke-turtle/f5-tts-hindhi
f5-tts-hindhi is a text-to-speech model from SwarajSolanke-turtle. Use it when you need text read aloud. It is set up for f5-tts. The card lists the license as cc-by-4.0.
Fine-tuned F5-TTS model for Hindi text-to-speech. - Base model: SPRINGLab/F5-Hindi-24KHz (151M params, F5-TTS Small) - Datasets: IndicTTS-Hindi + IndicVoices-RHindi - Learning rate: 1e-05 - Epochs: 10 - Batch size: 20…
All-time downloads
540
Public
Repo size
12.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt10.1 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- f5-tts
- License
- cc-by-4.0
- Access
- Public
- Created
- Jun 1, 2026
- Updated
- Jun 2, 2026
- SHA
- 4d4cdcd8
Base models
Model card
From the Hugging Face model README
F5-TTS Hindi
Fine-tuned F5-TTS model for Hindi text-to-speech.
Training Details
- Base model: SPRINGLab/F5-Hindi-24KHz (151M params, F5-TTS Small)
- Datasets: IndicTTS-Hindi + IndicVoices-R_Hindi
- Learning rate: 1e-05
- Epochs: 10
- Batch size: 200 frames/GPU
- Architecture: DiT (dim=768, depth=18, heads=12) + ConvNeXt V2 (dim=512, layers=4)
- Audio: 24kHz, 100-dim mel spectrogram, Vocos vocoder
Usage
from f5_tts.api import F5TTS
model = F5TTS(
model="F5-TTS",
ckpt_file="path/to/model_last.pt",
vocab_file="path/to/vocab.txt",
)
wav, sr, _ = model.infer(
ref_file="reference.wav",
ref_text="संदर्भ पाठ हिंदी में",
gen_text="आपका दिन शुभ हो",
)
training loss
- Task
- Text-to-Speech
- Library
- f5-tts
- License
- cc-by-4.0
- Languages
- hi
- Created
- Jun 1, 2026
- Updated
- Jun 2, 2026