Downloads · 30 days
9
22% of all-time downloads
iaratts-sft-v3
marcosremar2/iaratts-sft-v3
iaratts-sft-v3 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.
Brazilian Portuguese TTS with paralinguistic tag rendering — full SFT of MOSS-TTS-Nano-100M with vocab extended for nonverbal tokens.
All-time downloads
41
Public
Repo size
286 MB
Likes
0
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
- f4312fbf
Base models
Model card
From the Hugging Face model README
IaraTTS — SFT v3 (PoC MVP, paralinguistic tags)
Brazilian Portuguese TTS with paralinguistic tag rendering — full SFT of MOSS-TTS-Nano-100M with vocab extended for nonverbal tokens.
What's new vs v1/v2
- Special tokens added:
<sigh>,<laugh>,<yawn>,<gasp>,<groan>,<chuckle>,<cough>,<sniffle>registered as single token IDs (16384–16391). Tokenizer no longer fragments them into BPE pieces. - Trained 10 epochs at lr=5e-5 (vs 3 epochs lr=5e-5 in v1, 5 epochs lr=3e-5 in v2). 1530 steps total, ~30 min on RTX 4090.
- Loss trajectory: 5.02 → 4.51 (better than v2's 4.84).
- Coverage: 4869 train pairs, 51% with instruction/tag conditioning.
Qualitative test (9 demo prompts)
User feedback: nonverbal sounds (sigh/laugh/yawn/gasp/chuckle/groan) render audibly in v3 — partial quality, not perfect, but the tag→sound mapping is working. v1/v2 produced only speech without the tag sound.
Training
| Hyperparam | Value |
|---|---|
| Base model | OpenMOSS-Team/MOSS-TTS-Nano-100M (vocab extended to 16392) |
| Codec | OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano |
| Dataset | marcosremar2/gemini-dataset-erinome (4869 pairs after intersection) |
| per_device_batch_size | 8 |
| gradient_accumulation_steps | 4 |
| global_batch_size | 32 |
| epochs | 10 (1530 steps) |
| learning_rate | 5e-5 cosine, warmup 5% |
| mixed_precision | bf16 |
| attn_implementation | sdpa |
| GPU | RTX 4090 (Vast.ai, ~$0.07/hr) |
| Wall time | ~30 min |
| Loss | 5.02 → 4.51 |
| Total cost | ~$0.04 |
Special token integration
The MOSS-TTS-Nano text_lm_head layer was resized from (16384, 768) → (16392, 768). New embeddings initialized from multivariate normal (mean+covariance of existing embeddings, per Hewitt 2021 vocab expansion technique). Both vocab_size and nested gpt2_config.vocab_size updated in config.json.
Open issues / next iterations
- Tag rendering quality: ~50–60% rate, not 100%. Needs more epochs (15–20) or upsampling of tagged examples in training set.
- WER on holdout not yet measured with v3 (eval rounds 30–60 prompts pending).
- Phase 3.6 (Meta Quest viseme stream) and Phase 3.7 (style continuity hybrid) still to implement.
Inference
from transformers import AutoModel, AutoTokenizer
m = AutoModel.from_pretrained("marcosremar2/iaratts-sft-v3", trust_remote_code=True)
t = AutoTokenizer.from_pretrained("marcosremar2/iaratts-sft-v3", trust_remote_code=True)
# tags work as single tokens now:
ids = t.encode("<sigh> Que cansaço.", add_special_tokens=False)
# -> [16384, ..., space, ..., Que, ..., cansaço, ...]
CLI via MOSS infer.py:
python infer.py --checkpoint marcosremar2/iaratts-sft-v3 \
--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
Related
- v1: marcosremar2/iaratts-sft-v1 — Phase 2 baseline (3 epochs, no tags)
- Roadmap: marcosremar2/iaratts-roadmap
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