ampixa/sanoTTS

web: pinyin Chinese voice bundle (zh-xiaoya, 1,554,284 params, f16)

Chinese voice distilled from the pinyin teacher (zh-xiaoya-1p55m)

gguf: add the hi piperlite voice for audio.cpp

gguf: add the ne piperlite voice for audio.cpp

gguf: nine piperlite language voices for audio.cpp (cs, de, es, fr, it, pt, ro, ru, tr)

Voice bundles at float16, and the eight ~511k variants

Add ten new-language voice bundles for the browser demo

Add 18 voices in 10 new languages (de, tr, ru, fr, es, it, pt, ro, cs, ar)

gguf: id config

gguf: add id piperlite FP32 (audio.cpp package)

gguf: vi config

gguf: add vi piperlite FP32 (audio.cpp package)

gguf: kristin config

gguf: add kristin piperlite FP32 (audio.cpp package)

gguf: hfc config

gguf: add hfc piperlite FP32 (audio.cpp package)

gguf: amy config

gguf: add amy piperlite FP32 (audio.cpp package)

gguf: re-embed the two-package model spec in heart-nano

gguf: heart config

gguf: add heart 2.27M FP32 (audio.cpp package)

gguf: embed the audio.cpp model spec (standalone package)

gguf: add audiocpp exact tensor shape metadata (fixes trailing-1 dim squeeze)

FP32 GGUF with PyTorch-shaped tensors, for ggml consumers

FP32 GGUF with PyTorch-shaped tensors, for ggml consumers

card: npm 0.3.0 streams weights from here too

web: browser-format voice blobs so sanotts-web can fetch weights from here

config.json: carry tensor->offset regions so consumers need no name translation

Add sanoTTS GGUF config.json for audio.cpp

Add sanoTTS nano GGUF packaging for audio.cpp

Add sanoTTS nano GGUF packaging for audio.cpp

Add sanoTTS nano GGUF packaging for audio.cpp

samples: drop the mislabelled 745k filename, superseded by mcu-567k.mp3

card: 294k-2.27M range, heart + heart-nano, HF-first downloads, 567,008 on-device count

evidence: diverse24 re-measurement for heart and heart-nano

samples: rename mcu-745k to the audited 567,008 count

samples: add heart (2.27M) and heart-nano (294k) clips

Add heart voice package (nano runtime: meta.json + offsets header + int8/fp32 blobs)

Add heartnano voice package (nano runtime: meta.json + offsets header + int8/fp32 blobs)

Rebuild model card: samples table with embedded audio players, install table, links

Add voice sample audio clips (16 language/voice + mcu-745k)

sanoTTS voice packages: 7 voices, 6 languages, 1.08M-1.84M params

initial commit