GRT-30M-TTS (MatterWaveAI/grt-30m-tts)

GRT-30M-TTS is a 100% Native Rotational Text-to-Speech & Speech-Equipped Language Model (29,352,859 total parameters, zero nn.Linear layers, zero nn.Conv1d layers) built on top of MatterWaveAI/grt-30m.

Architecture Summary

Component	Module	Parameters	Geometry
Language Backbone	GRTModel + GRTCosineHead	29,305,498	12-layer causal Givens Rotational Transformer (MatterWaveAI/grt-30m, frozen to preserve 100% text fluency)
Polar Vocoder Head	GRTPolarVocoderHead (model.speech_head)	47,361	15-stage Givens butterfly expand → GRTRadialGELU → 15-stage butterfly contract (frames_per_token=4, 128 (Re, Im) STFT bins → torch.istft @ 16 kHz)
Total (GRT-30M-TTS)	GRTTTSForConditionalGeneration	29,352,859	0 nn.Linear, 0 nn.Conv1d

Speech Synthesis Alignment Metrics (HessianPairAdam / Sophia-Torus)

• Frame Polar Cosine Similarity: -0.0779 (unaligned) → 0.9874 (aligned)
• Utterance Polar Cosine Similarity: -0.0772 → 0.9684
• Magnitude Envelope Cosine Similarity: 0.9843
• Spectral SNR: -6.99 dB → 12.03 dB

Quickstart (transformers)

import torch
from transformers import AutoTokenizer, GRTTTSForConditionalGeneration

model_id = "MatterWaveAI/grt-30m-tts"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = GRTTTSForConditionalGeneration.from_pretrained(model_id, dtype=torch.float32)

prompt = "<|im_start|>user\nSpeak (alto, declarative): hello matter wave<|im_end|>\n<|im_start|>assistant\n"
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
outputs = model(**inputs)
print("Synthesized waveform shape:", outputs.speech_waveform.shape)

---

Complete MatterWaveAI/grt-30m* Research Suite on Hugging Face

1. Base Causal LM: MatterWaveAI/grt-30m
2. Chat Fine-Tune: MatterWaveAI/grt-30m-chat
3. 4-Expert Mixture-of-Rotations (MoR): MatterWaveAI/grt-30m-mor
4. Circular-Pooled Sentence Embedding: MatterWaveAI/grt-30m-embedding
5. Cross-Encoder Reranker: MatterWaveAI/grt-30m-reranker
6. Vision-Language (GRTVL): MatterWaveAI/grt-30m-vl
7. Canonical Tokenizer & Polar Embedding Bank: MatterWaveAI/grt-30m-tokenizer
8. Rotational Text-to-Speech (GRTTTS): MatterWaveAI/grt-30m-tts
9. Multimodal Vision-Audio-Language-Speech (GRTOmni): MatterWaveAI/grt-30m-omni

• Whitepaper: The Geometric Rotation Transformer (GRT): A Purely Rotational Foundation Architecture (GRT_Whitepaper.pdf)

---

License

Apache 2.0

---

Citation

@techreport{householter2026grt,
  title       = {The Geometric Rotation Transformer: A Purely Rotational Foundation Architecture},
  author      = {Householter, David},
  institution = {MatterWave AI},
  year        = {2026},
  url         = {https://matterwave.ai}
}