Upload 13 files

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+omnivoice-main.onnx_data_00 filter=lfs diff=lfs merge=lfs -text
+omnivoice-main.onnx_data_01 filter=lfs diff=lfs merge=lfs -text
+omnivoice-main.onnx_data_02 filter=lfs diff=lfs merge=lfs -text
+omnivoice-main.onnx_data_03 filter=lfs diff=lfs merge=lfs -text
+omnivoice-main.onnx_data_04 filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,55 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+tags:
+  - text-to-speech
+  - tts
+  - onnx
+  - voice-cloning
+  - browser
+  - webassembly
+  - webgpu
+language:
+  - en
+  - de
+  - zh
+  - ja
+  - fr
+  - es
+  - multilingual
+library_name: onnxruntime
+base_model: k2-fsa/OmniVoice
+---
+
+# VocoLoco — OmniVoice ONNX Models
+
+ONNX exports of [k2-fsa/OmniVoice](https://github.com/k2-fsa/OmniVoice) for browser-based text-to-speech inference via ONNX Runtime Web.
+
+## Models
+
+| File | Size | Description |
+|------|------|-------------|
+| `omnivoice-main-split.onnx` + `_data_00`-`_04` | 2.3 GB | Main TTS model (FP32, sharded) |
+| `omnivoice-main-int8.onnx` | 586 MB | Main TTS model (INT8 quantized, for mobile/low-memory) |
+| `omnivoice-decoder.onnx` | 83 MB | Audio token decoder (tokens to waveform) |
+| `omnivoice-encoder-fixed.onnx` | 624 MB | Audio encoder for voice cloning |
+| `tokenizer.json` | 11 MB | Qwen2 BPE text tokenizer |
+
+## Usage
+
+These models are designed to run in the browser via [VocoLoco](https://github.com/YOUR_USERNAME/vocoloco), a fully client-side TTS application. No server required.
+
+## Architecture
+
+- **Backbone**: Qwen3-0.6B (28 transformer layers)
+- **Audio codec**: HiggsAudioV2 (8 codebooks, 24kHz output)
+- **Generation**: Iterative masked diffusion (configurable 8-32 steps)
+- **Voice cloning**: Zero-shot via reference audio encoding
+- **Voice design**: Text-based control (gender, pitch, accent)
+
+## License
+
+Apache 2.0 — same as the original OmniVoice model.
+
+## Attribution
+
+Based on [OmniVoice](https://github.com/k2-fsa/OmniVoice) by Xiaomi Corp (k2-fsa).

omnivoice-config.json

@@ -0,0 +1,17 @@
+{
+  "audio_vocab_size": 1025,
+  "audio_mask_id": 1024,
+  "num_audio_codebook": 8,
+  "audio_codebook_weights": [
+    8,
+    8,
+    6,
+    6,
+    4,
+    4,
+    2,
+    2
+  ],
+  "sampling_rate": 24000,
+  "frame_rate": 75
+}

omnivoice-decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd3ee3803ef7008a889cabdb7918c5490effc60f9d6816fa15a1266c637c03b
+size 86507879

omnivoice-encoder-fixed.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b492911cdec14af947bddc6723a866595641e5c240c7df76619ac22ee39ad0
+size 654406661

omnivoice-main-manifest.json

@@ -0,0 +1 @@
+["omnivoice-main.onnx_data_00", "omnivoice-main.onnx_data_01", "omnivoice-main.onnx_data_02", "omnivoice-main.onnx_data_03", "omnivoice-main.onnx_data_04"]

omnivoice-main-split.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659d29a18d911b4f6c16ca38cc85f1f4d8916bd4c570f4c4962d99c4a4703365
+size 1312786

omnivoice-main.onnx_data_00

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91f303a39a137f3fcf8bfe5001e2c0bff6a94f6a64caa7184841423b76787f9
+size 621264896

omnivoice-main.onnx_data_01

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07aae92a349055ca40388e07b383fcbfc3020762ba983abe884299ad539a948f
+size 511971328

omnivoice-main.onnx_data_02

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2858726c56749de3e1a1f5180267641275668e55ff685f30b790a995649f426
+size 515899392

omnivoice-main.onnx_data_03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c4a8772b6c76914d05929fe28d0d59b562baafaef32b953845a1402042ddf9
+size 524288000

omnivoice-main.onnx_data_04

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ab213e97b72b08388f6c06bb12c0eb9a00a49df0850d3e6cf665fb58b37fda
+size 276856832

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408f669b7e2b045fdf54201d815bd364e6667dbd845115da81239c40bc6dcfd1
+size 11423986

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|denoise|>",
+    "<|lang_start|>",
+    "<|lang_end|>",
+    "<|instruct_start|>",
+    "<|instruct_end|>",
+    "<|text_start|>",
+    "<|text_end|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}