Add files using upload-large-folder tool

README.md

@@ -0,0 +1,108 @@
+---
+license: other
+base_model: KittenML/kitten-tts-mini-0.8
+tags:
+  - rlx
+  - text-to-speech
+  - onnx
+  - safetensors
+library_name: rlx-models
+---
+
+# Kitten TTS mini 0.8 — RLX bundle
+
+RLX compile bundle for [KittenML/kitten-tts-mini-0.8](https://huggingface.co/KittenML/kitten-tts-mini-0.8). Replaces ONNX Runtime at inference time: `rlx-kittentts` loads `graph.json` + `weights.safetensors`, lowers to RLX HIR, and compiles with `rlx-runtime`.
+
+**Upstream weights (required):** download [KittenML/kitten-tts-mini-0.8](https://huggingface.co/KittenML/kitten-tts-mini-0.8) for `config.json` and `voices.npz`.
+
+## Files
+
+| File | Description |
+|------|-------------|
+| `graph.json` | RLX graph IR (3006 nodes) |
+| `weights.safetensors` | Decomposed model weights (~350 MB) |
+| `manifest.json` | Export metadata (op histogram, I/O shapes) |
+
+## Quick start
+
+```bash
+# 1. Upstream ONNX checkpoint + voices
+huggingface-cli download KittenML/kitten-tts-mini-0.8 --local-dir .cache/kittentts-mini-0.8
+
+# 2. This RLX bundle (merge into the same directory)
+huggingface-cli download eugenehp/kitten-tts-mini-0.8-rlx --local-dir .cache/kittentts-mini-0.8
+
+# 3. Sentinel file for native auto-detection (same bytes as weights.safetensors)
+ln -sf weights.safetensors .cache/kittentts-mini-0.8/model.safetensors
+
+# 4. Synthesize (from rlx-models checkout)
+cargo run -p rlx-kittentts --features native --release -- \
+  --model-dir .cache/kittentts-mini-0.8 \
+  --native --ipa "həˈloʊ" --voice Jasper --out-wav out.wav
+```
+
+Or with `just`:
+
+```bash
+just fetch-kittentts
+huggingface-cli download eugenehp/kitten-tts-mini-0.8-rlx \
+  --local-dir .cache/kittentts-mini-0.8
+ln -sf weights.safetensors .cache/kittentts-mini-0.8/model.safetensors
+just kittentts -- --native --ipa "həˈloʊ" --out-wav /tmp/out.wav
+```
+
+## Layout after merge
+
+```text
+.cache/kittentts-mini-0.8/
+  config.json              # from KittenML
+  voices.npz               # from KittenML
+  kitten_tts_mini_v0_8.onnx
+  model.safetensors        # symlink → weights.safetensors
+  graph.json               # this repo
+  manifest.json
+  weights.safetensors
+```
+
+Alternatively, keep `rlx_bundle/` as a subdirectory and set `RLX_ONNX_BUNDLE` to that path.
+
+## Environment variables
+
+| Variable | Purpose |
+|----------|---------|
+| `RLX_KITTENTTS_DIR` | Model directory (default: `.cache/kittentts-mini-0.8`) |
+| `RLX_ONNX_BUNDLE` | Bundle directory if not co-located with weights |
+| `KITTEN_RLX_WEIGHTS` | Directory containing `model.safetensors` |
+| `KITTEN_RLX_BUNDLE` | Legacy alias for `RLX_ONNX_BUNDLE` |
+
+## Re-export
+
+From [MIT-RLX/rlx-models](https://github.com/MIT-RLX/rlx-models):
+
+```bash
+just fetch-kittentts
+just export-kitten-rlx-bundle
+```
+
+Requires: `pip install onnx onnxshape numpy safetensors`
+
+## Crates
+
+| Crate | Role |
+|-------|------|
+| [`kitten_tts_mini_rlx`](https://crates.io/crates/kitten_tts_mini_rlx) | Bundle → HIR → compile |
+| [`rlx-kittentts`](https://crates.io/crates/rlx-kittentts) | CLI + library (`--features native`) |
+
+## Inputs / outputs
+
+| Tensor | Shape | dtype |
+|--------|-------|-------|
+| `input_ids` | `[1, sequence_length]` | i64 |
+| `style` | `[1, 256]` | f32 |
+| `speed` | `[1]` | f32 |
+| `waveform` | `[num_samples]` | f32 (output) |
+| `duration` | dynamic | i64 (output) |
+
+## License
+
+Derived from [KittenML/kitten-tts-mini-0.8](https://huggingface.co/KittenML/kitten-tts-mini-0.8) — follow the upstream model license. RLX tooling ([rlx-models](https://github.com/MIT-RLX/rlx-models)) is GPL-3.0.

manifest.json

@@ -0,0 +1,141 @@
+{
+  "source_onnx": "KittenML/kitten-tts-mini-0.8:kitten_tts_mini_v0_8.onnx",
+  "opset": [
+    [
+      "",
+      20
+    ],
+    [
+      "ai.onnx.ml",
+      5
+    ],
+    [
+      "ai.onnx.training",
+      1
+    ],
+    [
+      "ai.onnx.preview.training",
+      1
+    ],
+    [
+      "com.microsoft",
+      1
+    ],
+    [
+      "com.microsoft.experimental",
+      1
+    ],
+    [
+      "com.microsoft.nchwc",
+      1
+    ],
+    [
+      "org.pytorch.aten",
+      1
+    ]
+  ],
+  "inputs": [
+    {
+      "name": "input_ids",
+      "shape": [
+        1,
+        "sequence_length"
+      ],
+      "dtype": "i64"
+    },
+    {
+      "name": "style",
+      "shape": [
+        1,
+        256
+      ],
+      "dtype": "f32"
+    },
+    {
+      "name": "speed",
+      "shape": [
+        1
+      ],
+      "dtype": "f32"
+    }
+  ],
+  "outputs": [
+    {
+      "name": "waveform",
+      "shape": [
+        "num_samples"
+      ],
+      "dtype": "f32"
+    },
+    {
+      "name": "duration",
+      "shape": [
+        "Castduration_dim_0"
+      ],
+      "dtype": "i64"
+    }
+  ],
+  "node_count": 3006,
+  "initializer_count": 1140,
+  "op_histogram": {
+    "SequenceEmpty": 1,
+    "Shape": 88,
+    "Gather": 148,
+    "Cast": 251,
+    "Reshape": 192,
+    "Slice": 144,
+    "Transpose": 91,
+    "DynamicQuantizeLinear": 125,
+    "Squeeze": 4,
+    "Range": 7,
+    "Unsqueeze": 131,
+    "Mul": 637,
+    "MatMul": 163,
+    "Concat": 77,
+    "ConstantOfShape": 14,
+    "Equal": 12,
+    "Add": 467,
+    "Where": 22,
+    "ReduceMax": 1,
+    "Loop": 1,
+    "Expand": 15,
+    "ConcatFromSequence": 1,
+    "TopK": 1,
+    "ReduceProd": 1,
+    "LayerNormalization": 31,
+    "ScatterElements": 1,
+    "Greater": 3,
+    "Not": 1,
+    "ConvInteger": 74,
+    "ScatterND": 3,
+    "LeakyRelu": 28,
+    "Sub": 5,
+    "Sqrt": 25,
+    "Div": 30,
+    "Softmax": 12,
+    "Pow": 50,
+    "DynamicQuantizeLSTM": 6,
+    "Tanh": 13,
+    "InstanceNormalization": 55,
+    "Sigmoid": 1,
+    "ReduceSum": 1,
+    "Round": 1,
+    "Clip": 1,
+    "SplitToSequence": 2,
+    "Resize": 6,
+    "ConvTranspose": 7,
+    "If": 2,
+    "Conv": 4,
+    "Floor": 1,
+    "RandomUniformLike": 1,
+    "CumSum": 1,
+    "Sin": 39,
+    "RandomNormalLike": 1,
+    "Pad": 2,
+    "Less": 1,
+    "Atan": 1,
+    "And": 1,
+    "Exp": 1,
+    "Cos": 1
+  }
+}

weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a49eda8e7cbcd24b96f4ad18fe5028a00f26b9f204a67abc9a9a220bbb6c15
+size 366599892