Reza2kn/gooya-v1-ONNX-fp16

Gooya v1 — ONNX WebGPU FP16

Browser-ready ONNX export of Reza2kn/gooya-v1, with the required MOSS audio codec and the Negara v7 Persian G2P frontend.

New long-form checkpoint

This export was created from the new source revision 9320f582245d8877f207d5609ff3ca1391c7085f using exactly:

• Transformers 4.57.1
• PyTorch 2.12.0
• ONNX opset 17
• all 16 MOSS audio codebooks

The fixed browser sampler bakes the checkpoint card's cooler long-form defaults: audio temperature 0.6, top-p 0.9, top-k 25, and repetition penalty 1.2. Do not recreate it with Transformers 5.x; this remote-code model is verified with Transformers 4.57.1.

Repository layout

MOSS-TTS-Nano-100M-ONNX/       FP16 TTS graphs + shared external weights
MOSS-Audio-Tokenizer-Nano-ONNX/ FP16 full decoder + FP32 encoder/streaming decoder
negara-g2p-v7/onnx/            Persian grapheme-to-phoneme ONNX graphs
validation/                     corrected and broken comparison WAVs

The TTS graphs use FP16 internal weights and FP32 graph I/O for WebGPU compatibility. The full codec decoder is FP16; the reference encoder and streaming decoder remain FP32. A smaller INT4 TTS derivative exists, but FP16 is the recommended WebGPU path because measured autoregressive generation is substantially faster in ONNX Runtime Web 1.27.

Validation

Input: سلام. → s a l A m, fixed sampling, seed 1234, all 16 codebooks.

Build	Frames	Termination	Persian Whisper result
New checkpoint FP16	22	audio EOS	سالو (Whisper-base smoke)
New checkpoint INT4 block-64	15	audio EOS	سالا (Whisper-base smoke)
New checkpoint INT4 block-32	17	audio EOS	سالام (Whisper-base smoke)

Actual browser profiling on the included 68-character Persian demo, ONNX Runtime Web 1.27 WebGPU:

• FP16 synthesis pipeline: 10.86 s before GPU-resident KV-cache optimization
• FP16 synthesis pipeline: 6.22 s with GPU-resident KV cache
• INT4 block-32 synthesis pipeline: 33.28 s; smaller download, but not the speed default
• greedy Negara G2P matched 5-beam output on five representative Persian sentences while reducing warm G2P latency from 6.7–8.1 s to 1.3–1.8 s

The web app overlaps G2P with model loading, caches shared sidecar reads, compiles only the active sampler, keeps autoregressive KV tensors on GPU, and prewarms after the first text interaction.

License

This derivative follows the source model's other license classification. Review the upstream Gooya and OpenMOSS licensing terms before redistribution or commercial use.