Downloads · 30 days
12
16% of all-time downloads
iaratts-sft-v4
marcosremar2/iaratts-sft-v4
iaratts-sft-v4 is a text-to-speech model from marcosremar2. Use it when you need text read aloud. It is set up for transformers. The card lists the license as mit.
- 7449 samples (3579 original + 3870 upsampled tagged) - 3x upsampling on <laugh, <sigh, <yawn, <gasp, <groan, <chuckle, <cough, <sniffle - Vocab 16384 → 16392 (8 special tokens single-id) - 15 epochs, 3495 steps, lr…
All-time downloads
76
Public
Repo size
286 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin285 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- mit
- Model type
- moss_tts_nano
- Access
- Public
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026
- SHA
- e92e473c
Base models
Model card
From the Hugging Face model README
IaraTTS SFT v4 — 15 epochs + 3x tag upsampling
Eval results (60-prompt pt-BR holdout, Whisper-base round-trip)
| Model | WER | Δ vs v3 |
|---|---|---|
| SFT v3 (10 epochs) | 0.1928 | baseline |
| SFT v4 (this) | 0.1646 | −14.6% relative |
Training
- 7449 samples (3579 original + 3870 upsampled tagged)
- 3x upsampling on
<laugh>,<sigh>,<yawn>,<gasp>,<groan>,<chuckle>,<cough>,<sniffle> - Vocab 16384 → 16392 (8 special tokens single-id)
- 15 epochs, 3495 steps, lr 5e-5 cosine + warmup 5%, bf16 sdpa
- ~70 min on RTX 4090, ~$0.30 GPU
Inference
from transformers import AutoModel, AutoTokenizer
m = AutoModel.from_pretrained("marcosremar2/iaratts-sft-v4", trust_remote_code=True)
t = AutoTokenizer.from_pretrained("marcosremar2/iaratts-sft-v4", trust_remote_code=True)
# Tags as single tokens:
ids = t.encode("<laugh> Que dia! Estou exausto.", add_special_tokens=False)
CLI via MOSS infer.py:
python infer.py --checkpoint marcosremar2/iaratts-sft-v4 \
--audio-tokenizer-pretrained-name-or-path OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano \
--text "<sigh> Encontrei um erro no código." \
--output-audio-path out.wav --mode continuation --seed 42
Roadmap position
Phase 4 wave complete. Next: Phase 4.4 (IndexTTS2 instruction LM) or Phase 5.5 (CosyVoice-2 distill to 150M streaming).
License: MIT (same as upstream MOSS-TTS-Nano).
- Task
- Text-to-Speech
- Library
- transformers
- Type
- moss_tts_nano
- License
- mit
- Languages
- pt
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026