Sonora
Sonora is a lightweight, non-autoregressive text-to-speech (TTS) model line built for real-time, on-device, and resource-constrained environments — the voice engine of Project Prosodia. Architecture:...
Fuente del modelo
- Tipo
- Other
- Tamaño del archivo
- 61,8 KB–113 MB
- Versión
- vRevision 149acc1
- Actualizado
- 19 oct 2026
- Descargas
- 47
- Fuente
- Hugging Face
Descripción de la fuente
Sonora
Sonora is a lightweight, non-autoregressive text-to-speech (TTS) model line built for real-time, on-device, and resource-constrained environments — the voice engine of Project Prosodia. Architecture: Matcha-TTS-family Optimal-Transport Conditional Flow Matching (OT-CFM) acoustic model + HiFi-GAN vocoder, with a growing set of expressive conditioning channels (valence / arousal-energy / tension via FiLM) aimed at directable, story-driven narration.
This repository is the model registry: each top-level directory is one promoted, audited milestone artifact with its own README, eval report, and provenance.
Registry index
Current trunk:
derisk-energy-24k(acoustic) +vocoder-24k-hifigan(vocoder) — the 24 kHz multi-speaker line. Next up: the v1.1 VAT continuation (story-driven valence corpus), warm-starting fromvat3-24k. Machine-readable lineage:registry.json.
| Directory | Training pass | What it is | Status |
|---|---|---|---|
baseline-ljspeech-22k/ | Phase 0 | Single-speaker LJSpeech fine-tune, 22.05 kHz, end-to-end graphs (ONNX + TFLite) and the LiteRT split-graph mobile lane. (Renamed from v1-ljspeech on 2026-07-22 — update old deep links.) | Published 2026-07-12 |
vocoder-24k-hifigan/ | 24 kHz trunk — vocoder | HiFi-GAN vocoder fine-tune, 24 kHz / 80-band — the vocoder pairing for the multi-speaker line. Converged + human-audited (copy-synthesis A/B indistinguishable). | Published 2026-07-16 |
derisk-energy-24k/ | Expressive de-risk (north-star §7) | First trained expressive channel: energy/arousal FiLM conditioning, multi-speaker (247 spk, LibriTTS-R), 24 kHz. Controllability ρ≈1.0, identity-preserving, WER-safe; includes the VAT-ready LiteRT split-graph export. | Published 2026-07-16 |
vat3-24k/ | Full 3-channel VAT (milestone 3) | First all-three-channels training (valence/energy/tension FiLM), warm-started from derisk-energy-24k. Mixed verdict: energy PASS, tension near-pass, valence FAIL — a corpus-label limitation, not a training one (see its README). Warm-start seed for the v1.1 continuation. | Published 2026-07-22 |
Directory names are deliberately descriptive, not phase-numbered — artifacts keep their identity even as the roadmap's phase labels evolve; the "Training pass" column carries the roadmap mapping.
Developed by: Artificial Humanity · License: Apache-2.0 · Languages: English
Model line at a glance
- Phase 0 (
baseline-ljspeech-22k) proved the on-device lane: ~18.2M-parameter acoustic model, single forward pass text→PCM, running on phones via TFLite/LiteRT. - The 24 kHz multi-speaker line (
vocoder-24k-hifigan+derisk-energy-24k) is the current trunk: native 24 kHz, 247 speakers, and validated FiLM conditioning — the de-risk experiment demonstrated a continuous, monotonic, speaker-preserving loudness/ energy control learned from weak labels in ~35 GPU-hours on consumer hardware. - Full 3-channel VAT conditioning (valence/arousal/tension) and story-driven expressive training data (directed teacher synthesis + aligned public-domain audiobooks) are in active development; artifacts land here as they pass their gates.
Provenance & audit culture
Every artifact directory documents: training corpus + license wall, warm-start lineage, pre-registered convergence criteria, automated eval-harness results (controllability / identity leakage / intelligibility), and human audition verdicts. Checkpoints are distributed as safetensors (weights-only); full resumable training checkpoints are retained privately.
Companion dataset
The sonora-expressive-registers dataset (CC-BY-4.0) — certified keeps from our
directed teacher-synthesis pipeline, with exact intended-VAT labels and full render
provenance — is published separately under this organization.
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 19 oct
Download files
Artefactos del modelo
7 artefactos
Artefactos del modelo
7 artefactosbaseline-ljspeech-22k/checkpoint_epoch=199_e2e.onnx
onnx · 113 MB · SHA-256 bd024a2e390f…6647 · Hugging Face
Download filebaseline-ljspeech-22k/litert-split/emb.bin
bin · 134 KB · SHA-256 a66495ff8e7e…a69c · Hugging Face
Download filederisk-energy-24k/litert-split/emb.bin
bin · 134 KB · SHA-256 d5ceea9dbdcd…c24f · Hugging Face
Download filederisk-energy-24k/litert-split/spk_emb.bin
bin · 61,8 KB · SHA-256 e002f88370c8…f03f · Hugging Face
Download filederisk-energy-24k/model_epoch=099.safetensors
safetensors · 86,2 MB · SHA-256 0a3ff76ce03a…9b5d · Hugging Face
Download filevat3-24k/model_epoch=099.safetensors
safetensors · 86,2 MB · SHA-256 a7ecd4ca5b0e…214c · Hugging Face
Download filevocoder-24k-hifigan/g_02510000.pth
pth · 53,2 MB · SHA-256 1ff1c3036c95…e65a · Hugging Face
Download fileExtractos de fuentes
3 extractos
Extractos de fuentes
3 extractos--- language: - en license: apache-2.0 tags: - text-to-speech - tts - matcha-tts - flow-matching - tflite - onnx - audio - on-device - expressive-speech datasets: - ljspeech - libritts_r metrics: - loss - wer pipeline_tag: text-to-speech --- # Sonora **Sonora** is a lightweight, non-autoregressive text-to-speech (TTS) model line built for real-time, on-device, and resource-constrained environments — the voice engine of **Project Prosodia**. Architecture: Matcha-TTS-family Optimal-Transport Conditional Flow Matching (OT-CFM) acoustic model + HiFi-GAN vocoder, with a growing set of **expressive conditioning channels** (valence / arousal-energy / tension via FiLM) aimed at directable, story-driven narration. This repository is the **model registry**: each top-level directory is one promoted, audited milestone artifact with its own README, eval report, and provenance. ## Registry index > **Current trunk:** `derisk-energy-24k` (acoustic) + `vocoder-24k-hifigan` (vocoder) — > the 24 kHz multi-speaker line. Next up: the v1.1 VAT continuation (story-driven valence > corpus), warm-starting from `vat3-24k`. > Machine-readable lineage: [`registry.json`](./registry.json). | Directory | Training pass | What it is | Status | |---|---|---|---| | [`baseline-ljspeech-22k/`](./baseline-ljspeech-22k) | **Phase 0** | Single-speaker LJSpeech fine-tune, 22.05 kHz, end-to-end graphs (ONNX + TFLite) and the LiteRT split-graph mobile lane. *(Renamed from `v1-ljspeech` on 2026-07-22 — update old deep links.)* | Published 2026-07-12 | | [`vocoder-24k-hifigan/`](./vocoder-24k-hifigan) | 24 kHz trunk — vocoder | HiFi-GAN vocoder fine-tune, 24 kHz / 80-band — the vocoder pairing for the multi-speaker line. Converged + human-audited (copy-synthesis A/B indistinguishable). | Published 2026-07-16 | | [`derisk-energy-24k/`](./derisk-energy-24k) | **Expressive de-risk** (north-star §7) | First trained expressive channel: energy/arousal FiLM conditioning, multi-speaker (247 spk, LibriTTS-R), 24 kHz. Controllability ρ≈1.0, identity-preserving, WER-safe; includes the VAT-ready LiteRT split-graph export. | Published 2026-07-16 | | [`vat3-24k/`](./vat3-24k) | **Full 3-channel VAT** (milestone 3) | First all-three-channels training (valence/energy/tension FiLM), warm-started from `derisk-energy-24k`. **Mixed verdict**: energy PASS, tension near-pass, valence FAIL — a corpus-label limitatio...
Source context: 105 downloads · 0 likes · Pipeline text-to-speech · Repo artificial-humanity/Sonora
Source context: 47 downloads · 0 likes · Pipeline text-to-speech · Repo artificial-humanity/Sonora
