Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+license: mit
+tags:
+- webgpu
+- wasm
+- in-browser
+- asr
+- tts
+- vad
+- speech
+- fluidaudio
+---
+
+# FluidAudio Web — raw model weights
+
+Model weights for **[fluidaudio-web](https://github.com/FluidInference/fluidaudio-web)**:
+fully in-browser inference (WebGPU + WebAssembly) for FluidAudio's speech models.
+
+These are **raw weights only — no ONNX, no onnxruntime.** Each engine is a
+hand-written forward pass (WebGPU/WASM/JS) that loads these tensors directly and,
+where applicable, dequantizes them in-shader. Weights are extracted from the
+source models and parity-verified against the originals before publishing.
+
+## Layout (one folder per engine)
+
+| folder | model | status |
+|---|---|---|
+| `vad/` | Silero VAD v5 (16 kHz) | ✅ available (fp32) |
+| `parakeet/` | Parakeet TDT 0.6B v3 (encoder + decoder/joint) | 🚧 in progress (int4/palettized) |
+| `kokoro/` | Kokoro TTS 82M | 🚧 planned |
+| `nemotron/` · `eou/` · `sortformer/` · `whisper/` | streaming ASR / EOU / diarization / multilingual ASR | 🚧 planned |
+
+## Format
+
+- `*.bin` — concatenated little-endian tensors.
+- `manifest.json` — `name -> { dims, offset, len }` (offset/len in **elements**, not bytes).
+
+Load: fetch the `.bin`, slice each tensor per the manifest. Extraction scripts and
+the forward passes live in the fluidaudio-web repo (`scripts/`, `src/engines/`).
+
+Quantized engines additionally carry per-tensor scales / palettes (documented per
+folder) for in-shader dequant.