VieNeu-TTS v3 Turbo β€” browser pack

Files repackaged so that VieNeu-TTS v3 Turbo can run entirely in a web browser with onnxruntime-web (WebAssembly). Nothing here was retrained; the weights are the upstream weights.

Sources

Part Upstream Licence
Acoustic model, tokenizer, preset voices pnnbao-ump/VieNeu-TTS-v3-Turbo, VieNeu-TTS Apache-2.0
Audio codec decoder OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano-ONNX Apache-2.0
Text normalisation and grapheme-to-phoneme sea-g2p Apache-2.0

What was changed

  • turbo/*.f16: the external weight files stored as float16, half the download. The browser expands them back to float32 before creating the ONNX sessions. The backbone and the embedding table were already float16 values upstream, so that part is lossless; the codec decoder is rounded once.
  • turbo/vieneu_acoustic_heads.onnx: upstream vieneu_acoustic_cached.onnx with five nodes appended that compute the logits of one codebook (Gather the last position, MatMul with the codebook's embedding table). In Python that product is a NumPy call; in a browser it has to live inside the graph to be fast. The embedding table is external data (vieneu_acoustic_heads.f16).
  • turbo/text_emb.f32, turbo/xvec.f32: arrays taken from upstream vieneu_v3_heads.npz.
  • turbo/voices.json: upstream voices_v3_turbo.json, same values, flat list.
  • g2p/sea_g2p.wasm: sea-g2p 0.10.0 built for wasm32-unknown-unknown through its C ABI, with a small patch so the dictionary can be handed over as bytes instead of a memory-mapped file.
  • g2p/sea_g2p.dictz: upstream sea_g2p.bin, gzip-compressed.

v1/manifest.json lists every file with its size and SHA-256.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support