Initial release: canto-tts-nano-v1 (CER 11.82% / tone 84.22% / code-switch CER 13.87%, N=5 repeat gate)

.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
+*.data filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

MOSS-Audio-Tokenizer-Nano-ONNX/.gitattributes

@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+*.data filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

MOSS-Audio-Tokenizer-Nano-ONNX/README.md

@@ -0,0 +1,118 @@
+---
+license: apache-2.0
+library_name: onnx
+tags:
+  - audio
+  - audio-tokenizer
+  - neural-codec
+  - moss-tts-family
+  - moss-audio-tokenizer-nano
+  - speech-tokenizer
+  - onnx
+  - onnxruntime
+  - browser
+---
+
+# MOSS-Audio-Tokenizer-Nano-ONNX
+
+This repository provides the **ONNX exports** of [MOSS-Audio-Tokenizer-Nano](https://huggingface.co/OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano), the lightweight audio tokenizer used by [MOSS-TTS-Nano](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano). It is intended for **torch-free** deployment with ONNX Runtime and ONNX Runtime Web.
+
+## Overview
+
+The Nano variant is a lightweight tokenizer with about **20M parameters**, designed to reduce deployment cost while preserving strong perceptual quality.
+
+MOSS-Audio-Tokenizer-Nano supports:
+
+- **48 kHz**, **stereo** audio
+- **12.5 Hz** token rate
+- **16 RVQ codebooks**
+- high-fidelity reconstruction across variable bitrates
+
+This ONNX repository is designed for lightweight inference pipelines such as:
+
+- local CPU deployment with `onnxruntime`
+- browser deployment with `onnxruntime-web`
+- companion audio encoding/decoding for `MOSS-TTS-Nano-100M-ONNX`
+
+## Supported Backends
+
+| Backend | Runtime | Use Case |
+|---------|---------|----------|
+| **ONNX Runtime (CPU)** | `onnxruntime` | Local CPU inference |
+| **ONNX Runtime Web** | `onnxruntime-web` | Browser-based deployment |
+
+## Repository Contents
+
+| File | Description |
+|------|-------------|
+| `moss_audio_tokenizer_encode.onnx` | Encoder graph for waveform -> discrete audio codes |
+| `moss_audio_tokenizer_encode.data` | External weights for the encoder graph |
+| `moss_audio_tokenizer_decode_full.onnx` | Full decoder graph for audio codes -> waveform |
+| `moss_audio_tokenizer_decode_step.onnx` | Streaming decoder-step graph for incremental decode |
+| `moss_audio_tokenizer_decode_shared.data` | External weights shared by the decoder graphs |
+| `codec_browser_onnx_meta.json` | Metadata for browser / ONNX runtime integration |
+
+## Quick Start
+
+```bash
+huggingface-cli download OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano-ONNX \
+    --local-dir weights/MOSS-Audio-Tokenizer-Nano-ONNX
+```
+
+This repository is typically used together with [OpenMOSS-Team/MOSS-TTS-Nano-100M-ONNX](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano-100M-ONNX) for fully torch-free MOSS-TTS-Nano deployment.
+
+## Main Repositories
+
+| Repository | Description |
+|------------|-------------|
+| [OpenMOSS/MOSS-TTS-Nano](https://github.com/OpenMOSS/MOSS-TTS-Nano) | MOSS-TTS-Nano source code and inference pipeline |
+| [OpenMOSS-Team/MOSS-TTS-Nano](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano) | PyTorch MOSS-TTS-Nano weights |
+| [OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano](https://huggingface.co/OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano) | PyTorch MOSS-Audio-Tokenizer-Nano weights |
+| [OpenMOSS-Team/MOSS-TTS-Nano-100M-ONNX](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano-100M-ONNX) | Companion ONNX TTS weights |
+
+## About MOSS-Audio-Tokenizer-Nano
+
+**MOSS-Audio-Tokenizer-Nano** serves as the lightweight codec backbone for MOSS-TTS-Nano. It keeps the same unified audio-token interface used across the MOSS-TTS family while reducing inference cost for CPU and browser deployment scenarios.
+
+For the original PyTorch implementation, setup instructions, and more background, see:
+
+- [MOSS-Audio-Tokenizer Repository](https://github.com/OpenMOSS/MOSS-Audio-Tokenizer)
+- [MOSS-TTS-Nano Repository](https://github.com/OpenMOSS/MOSS-TTS-Nano)
+
+## Citation
+
+If you use the MOSS-TTS work in your research or product, please cite:
+
+```bibtex
+@misc{openmoss2026mossttsnano,
+  title={MOSS-TTS-Nano},
+  author={OpenMOSS Team},
+  year={2026},
+  howpublished={GitHub repository},
+  url={https://github.com/OpenMOSS/MOSS-TTS-Nano}
+}
+```
+
+```bibtex
+@misc{gong2026mossttstechnicalreport,
+  title={MOSS-TTS Technical Report},
+  author={Yitian Gong and Botian Jiang and Yiwei Zhao and Yucheng Yuan and Kuangwei Chen and Yaozhou Jiang and Cheng Chang and Dong Hong and Mingshu Chen and Ruixiao Li and Yiyang Zhang and Yang Gao and Hanfu Chen and Ke Chen and Songlin Wang and Xiaogui Yang and Yuqian Zhang and Kexin Huang and ZhengYuan Lin and Kang Yu and Ziqi Chen and Jin Wang and Zhaoye Fei and Qinyuan Cheng and Shimin Li and Xipeng Qiu},
+  year={2026},
+  eprint={2603.18090},
+  archivePrefix={arXiv},
+  primaryClass={cs.SD},
+  url={https://arxiv.org/abs/2603.18090}
+}
+```
+
+```bibtex
+@misc{gong2026mossaudiotokenizerscalingaudiotokenizers,
+  title={MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models},
+  author={Yitian Gong and Kuangwei Chen and Zhaoye Fei and Xiaogui Yang and Ke Chen and Yang Wang and Kexin Huang and Mingshu Chen and Ruixiao Li and Qingyuan Cheng and Shimin Li and Xipeng Qiu},
+  year={2026},
+  eprint={2602.10934},
+  archivePrefix={arXiv},
+  primaryClass={cs.SD},
+  url={https://arxiv.org/abs/2602.10934}
+}
+```

MOSS-Audio-Tokenizer-Nano-ONNX/codec_browser_onnx_meta.json

@@ -0,0 +1,576 @@
+{
+  "format_version": 2,
+  "checkpoint_path": "MOSS-Audio-Tokenizer-Nano",
+  "files": {
+    "encode": "moss_audio_tokenizer_encode.onnx",
+    "decode_full": "moss_audio_tokenizer_decode_full.onnx",
+    "decode_step": "moss_audio_tokenizer_decode_step.onnx"
+  },
+  "external_data_files": {
+    "moss_audio_tokenizer_encode.onnx": [
+      "moss_audio_tokenizer_encode.data"
+    ],
+    "moss_audio_tokenizer_decode_full.onnx": [
+      "moss_audio_tokenizer_decode_shared.data"
+    ],
+    "moss_audio_tokenizer_decode_step.onnx": [
+      "moss_audio_tokenizer_decode_shared.data"
+    ]
+  },
+  "codec_config": {
+    "sample_rate": 48000,
+    "channels": 2,
+    "downsample_rate": 3840,
+    "num_quantizers": 16
+  },
+  "onnx": {
+    "opset": 17,
+    "encode_input_names": [
+      "waveform",
+      "input_lengths"
+    ],
+    "encode_output_names": [
+      "audio_codes",
+      "audio_code_lengths"
+    ],
+    "decode_input_names": [
+      "audio_codes",
+      "audio_code_lengths"
+    ],
+    "decode_output_names": [
+      "audio",
+      "audio_lengths"
+    ],
+    "decode_step_input_names": [
+      "audio_codes",
+      "audio_code_lengths",
+      "transformer_offset_0",
+      "transformer_offset_1",
+      "transformer_offset_2",
+      "transformer_offset_3",
+      "attn_offset_0",
+      "attn_cached_keys_0",
+      "attn_cached_values_0",
+      "attn_cached_positions_0",
+      "attn_offset_1",
+      "attn_cached_keys_1",
+      "attn_cached_values_1",
+      "attn_cached_positions_1",
+      "attn_offset_2",
+      "attn_cached_keys_2",
+      "attn_cached_values_2",
+      "attn_cached_positions_2",
+      "attn_offset_3",
+      "attn_cached_keys_3",
+      "attn_cached_values_3",
+      "attn_cached_positions_3",
+      "attn_offset_4",
+      "attn_cached_keys_4",
+      "attn_cached_values_4",
+      "attn_cached_positions_4",
+      "attn_offset_5",
+      "attn_cached_keys_5",
+      "attn_cached_values_5",
+      "attn_cached_positions_5",
+      "attn_offset_6",
+      "attn_cached_keys_6",
+      "attn_cached_values_6",
+      "attn_cached_positions_6",
+      "attn_offset_7",
+      "attn_cached_keys_7",
+      "attn_cached_values_7",
+      "attn_cached_positions_7",
+      "attn_offset_8",
+      "attn_cached_keys_8",
+      "attn_cached_values_8",
+      "attn_cached_positions_8",
+      "attn_offset_9",
+      "attn_cached_keys_9",
+      "attn_cached_values_9",
+      "attn_cached_positions_9",
+      "attn_offset_10",
+      "attn_cached_keys_10",
+      "attn_cached_values_10",
+      "attn_cached_positions_10",
+      "attn_offset_11",
+      "attn_cached_keys_11",
+      "attn_cached_values_11",
+      "attn_cached_positions_11"
+    ],
+    "decode_step_output_names": [
+      "audio",
+      "audio_lengths",
+      "transformer_offset_out_0",
+      "transformer_offset_out_1",
+      "transformer_offset_out_2",
+      "transformer_offset_out_3",
+      "attn_offset_out_0",
+      "attn_cached_keys_out_0",
+      "attn_cached_values_out_0",
+      "attn_cached_positions_out_0",
+      "attn_offset_out_1",
+      "attn_cached_keys_out_1",
+      "attn_cached_values_out_1",
+      "attn_cached_positions_out_1",
+      "attn_offset_out_2",
+      "attn_cached_keys_out_2",
+      "attn_cached_values_out_2",
+      "attn_cached_positions_out_2",
+      "attn_offset_out_3",
+      "attn_cached_keys_out_3",
+      "attn_cached_values_out_3",
+      "attn_cached_positions_out_3",
+      "attn_offset_out_4",
+      "attn_cached_keys_out_4",
+      "attn_cached_values_out_4",
+      "attn_cached_positions_out_4",
+      "attn_offset_out_5",
+      "attn_cached_keys_out_5",
+      "attn_cached_values_out_5",
+      "attn_cached_positions_out_5",
+      "attn_offset_out_6",
+      "attn_cached_keys_out_6",
+      "attn_cached_values_out_6",
+      "attn_cached_positions_out_6",
+      "attn_offset_out_7",
+      "attn_cached_keys_out_7",
+      "attn_cached_values_out_7",
+      "attn_cached_positions_out_7",
+      "attn_offset_out_8",
+      "attn_cached_keys_out_8",
+      "attn_cached_values_out_8",
+      "attn_cached_positions_out_8",
+      "attn_offset_out_9",
+      "attn_cached_keys_out_9",
+      "attn_cached_values_out_9",
+      "attn_cached_positions_out_9",
+      "attn_offset_out_10",
+      "attn_cached_keys_out_10",
+      "attn_cached_values_out_10",
+      "attn_cached_positions_out_10",
+      "attn_offset_out_11",
+      "attn_cached_keys_out_11",
+      "attn_cached_values_out_11",
+      "attn_cached_positions_out_11"
+    ]
+  },
+  "streaming_decode": {
+    "batch_size": 1,
+    "transformer_offsets": [
+      {
+        "index": 0,
+        "decoder_index": 1,
+        "input_name": "transformer_offset_0",
+        "output_name": "transformer_offset_out_0",
+        "shape": [
+          1
+        ],
+        "dtype": "int32"
+      },
+      {
+        "index": 1,
+        "decoder_index": 3,
+        "input_name": "transformer_offset_1",
+        "output_name": "transformer_offset_out_1",
+        "shape": [
+          1
+        ],
+        "dtype": "int32"
+      },
+      {
+        "index": 2,
+        "decoder_index": 5,
+        "input_name": "transformer_offset_2",
+        "output_name": "transformer_offset_out_2",
+        "shape": [
+          1
+        ],
+        "dtype": "int32"
+      },
+      {
+        "index": 3,
+        "decoder_index": 7,
+        "input_name": "transformer_offset_3",
+        "output_name": "transformer_offset_out_3",
+        "shape": [
+          1
+        ],
+        "dtype": "int32"
+      }
+    ],
+    "attention_caches": [
+      {
+        "index": 0,
+        "decoder_index": 1,
+        "layer_index": 0,
+        "context": 500,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_0",
+        "offset_output_name": "attn_offset_out_0",
+        "cached_keys_input_name": "attn_cached_keys_0",
+        "cached_keys_output_name": "attn_cached_keys_out_0",
+        "cached_values_input_name": "attn_cached_values_0",
+        "cached_values_output_name": "attn_cached_values_out_0",
+        "cached_positions_input_name": "attn_cached_positions_0",
+        "cached_positions_output_name": "attn_cached_positions_out_0",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          500,
+          64
+        ],
+        "positions_shape": [
+          1,
+          500
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 1,
+        "decoder_index": 1,
+        "layer_index": 1,
+        "context": 500,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_1",
+        "offset_output_name": "attn_offset_out_1",
+        "cached_keys_input_name": "attn_cached_keys_1",
+        "cached_keys_output_name": "attn_cached_keys_out_1",
+        "cached_values_input_name": "attn_cached_values_1",
+        "cached_values_output_name": "attn_cached_values_out_1",
+        "cached_positions_input_name": "attn_cached_positions_1",
+        "cached_positions_output_name": "attn_cached_positions_out_1",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          500,
+          64
+        ],
+        "positions_shape": [
+          1,
+          500
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 2,
+        "decoder_index": 1,
+        "layer_index": 2,
+        "context": 500,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_2",
+        "offset_output_name": "attn_offset_out_2",
+        "cached_keys_input_name": "attn_cached_keys_2",
+        "cached_keys_output_name": "attn_cached_keys_out_2",
+        "cached_values_input_name": "attn_cached_values_2",
+        "cached_values_output_name": "attn_cached_values_out_2",
+        "cached_positions_input_name": "attn_cached_positions_2",
+        "cached_positions_output_name": "attn_cached_positions_out_2",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          500,
+          64
+        ],
+        "positions_shape": [
+          1,
+          500
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 3,
+        "decoder_index": 1,
+        "layer_index": 3,
+        "context": 500,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_3",
+        "offset_output_name": "attn_offset_out_3",
+        "cached_keys_input_name": "attn_cached_keys_3",
+        "cached_keys_output_name": "attn_cached_keys_out_3",
+        "cached_values_input_name": "attn_cached_values_3",
+        "cached_values_output_name": "attn_cached_values_out_3",
+        "cached_positions_input_name": "attn_cached_positions_3",
+        "cached_positions_output_name": "attn_cached_positions_out_3",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          500,
+          64
+        ],
+        "positions_shape": [
+          1,
+          500
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 4,
+        "decoder_index": 3,
+        "layer_index": 0,
+        "context": 800,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_4",
+        "offset_output_name": "attn_offset_out_4",
+        "cached_keys_input_name": "attn_cached_keys_4",
+        "cached_keys_output_name": "attn_cached_keys_out_4",
+        "cached_values_input_name": "attn_cached_values_4",
+        "cached_values_output_name": "attn_cached_values_out_4",
+        "cached_positions_input_name": "attn_cached_positions_4",
+        "cached_positions_output_name": "attn_cached_positions_out_4",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          800,
+          64
+        ],
+        "positions_shape": [
+          1,
+          800
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 5,
+        "decoder_index": 3,
+        "layer_index": 1,
+        "context": 800,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_5",
+        "offset_output_name": "attn_offset_out_5",
+        "cached_keys_input_name": "attn_cached_keys_5",
+        "cached_keys_output_name": "attn_cached_keys_out_5",
+        "cached_values_input_name": "attn_cached_values_5",
+        "cached_values_output_name": "attn_cached_values_out_5",
+        "cached_positions_input_name": "attn_cached_positions_5",
+        "cached_positions_output_name": "attn_cached_positions_out_5",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          800,
+          64
+        ],
+        "positions_shape": [
+          1,
+          800
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 6,
+        "decoder_index": 5,
+        "layer_index": 0,
+        "context": 1200,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_6",
+        "offset_output_name": "attn_offset_out_6",
+        "cached_keys_input_name": "attn_cached_keys_6",
+        "cached_keys_output_name": "attn_cached_keys_out_6",
+        "cached_values_input_name": "attn_cached_values_6",
+        "cached_values_output_name": "attn_cached_values_out_6",
+        "cached_positions_input_name": "attn_cached_positions_6",
+        "cached_positions_output_name": "attn_cached_positions_out_6",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          1200,
+          64
+        ],
+        "positions_shape": [
+          1,
+          1200
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 7,
+        "decoder_index": 5,
+        "layer_index": 1,
+        "context": 1200,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_7",
+        "offset_output_name": "attn_offset_out_7",
+        "cached_keys_input_name": "attn_cached_keys_7",
+        "cached_keys_output_name": "attn_cached_keys_out_7",
+        "cached_values_input_name": "attn_cached_values_7",
+        "cached_values_output_name": "attn_cached_values_out_7",
+        "cached_positions_input_name": "attn_cached_positions_7",
+        "cached_positions_output_name": "attn_cached_positions_out_7",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          1200,
+          64
+        ],
+        "positions_shape": [
+          1,
+          1200
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 8,
+        "decoder_index": 7,
+        "layer_index": 0,
+        "context": 1600,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_8",
+        "offset_output_name": "attn_offset_out_8",
+        "cached_keys_input_name": "attn_cached_keys_8",
+        "cached_keys_output_name": "attn_cached_keys_out_8",
+        "cached_values_input_name": "attn_cached_values_8",
+        "cached_values_output_name": "attn_cached_values_out_8",
+        "cached_positions_input_name": "attn_cached_positions_8",
+        "cached_positions_output_name": "attn_cached_positions_out_8",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          1600,
+          64
+        ],
+        "positions_shape": [
+          1,
+          1600
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 9,
+        "decoder_index": 7,
+        "layer_index": 1,
+        "context": 1600,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_9",
+        "offset_output_name": "attn_offset_out_9",
+        "cached_keys_input_name": "attn_cached_keys_9",
+        "cached_keys_output_name": "attn_cached_keys_out_9",
+        "cached_values_input_name": "attn_cached_values_9",
+        "cached_values_output_name": "attn_cached_values_out_9",
+        "cached_positions_input_name": "attn_cached_positions_9",
+        "cached_positions_output_name": "attn_cached_positions_out_9",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          1600,
+          64
+        ],
+        "positions_shape": [
+          1,
+          1600
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 10,
+        "decoder_index": 7,
+        "layer_index": 2,
+        "context": 1600,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_10",
+        "offset_output_name": "attn_offset_out_10",
+        "cached_keys_input_name": "attn_cached_keys_10",
+        "cached_keys_output_name": "attn_cached_keys_out_10",
+        "cached_values_input_name": "attn_cached_values_10",
+        "cached_values_output_name": "attn_cached_values_out_10",
+        "cached_positions_input_name": "attn_cached_positions_10",
+        "cached_positions_output_name": "attn_cached_positions_out_10",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          1600,
+          64
+        ],
+        "positions_shape": [
+          1,
+          1600
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      },
+      {
+        "index": 11,
+        "decoder_index": 7,
+        "layer_index": 3,
+        "context": 1600,
+        "num_heads": 4,
+        "head_dim": 64,
+        "offset_input_name": "attn_offset_11",
+        "offset_output_name": "attn_offset_out_11",
+        "cached_keys_input_name": "attn_cached_keys_11",
+        "cached_keys_output_name": "attn_cached_keys_out_11",
+        "cached_values_input_name": "attn_cached_values_11",
+        "cached_values_output_name": "attn_cached_values_out_11",
+        "cached_positions_input_name": "attn_cached_positions_11",
+        "cached_positions_output_name": "attn_cached_positions_out_11",
+        "offset_shape": [
+          1
+        ],
+        "cache_shape": [
+          1,
+          4,
+          1600,
+          64
+        ],
+        "positions_shape": [
+          1,
+          1600
+        ],
+        "cache_dtype": "float32",
+        "positions_dtype": "int32"
+      }
+    ]
+  }
+}

MOSS-Audio-Tokenizer-Nano-ONNX/moss_audio_tokenizer_decode_full.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbbafe3fd4afa2a019af5c5ced204af6e2d1db044fa40f021525d2aee95b4ac
+size 681902

MOSS-Audio-Tokenizer-Nano-ONNX/moss_audio_tokenizer_decode_shared.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69d52e0f4e84ca27850557ee54face46632d3a5a16c89bd246c7c408466dcad
+size 44198912

MOSS-Audio-Tokenizer-Nano-ONNX/moss_audio_tokenizer_decode_step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9527c86a29e1837edec1f74db57d5eeaadb3a715af3382703566460afed25855
+size 351400

MOSS-Audio-Tokenizer-Nano-ONNX/moss_audio_tokenizer_encode.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa751265b2bab2887eac224484546b194875aa7494b607115439b3dc6b228a2c
+size 44507136

MOSS-Audio-Tokenizer-Nano-ONNX/moss_audio_tokenizer_encode.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadea4a645abdcf98714c7aead122ee2ce7da6e080f9f80b977cd1ca8e19473a
+size 815775

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_decode_step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245846789d1a7186c3087de756c38f698252dbafe47eb73ac243ee9df1292e81
+size 291483

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_global_shared.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf65e309adf12f837af995a7f81f6b13ded287af21763df9f9421c1c96c5137
+size 441083904

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_local_cached_step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66a3d8946d460b5bd859a1af3fc089819259c3684056bddc6640ffcf804b383
+size 53685

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_local_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05afc6a6f2f41981f1f1552fe772125b4dfc2bd3d13822ace45e17066f380480
+size 50194

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_local_fixed_sampled_frame.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3108436e014123ad860c17f841b24cf7b9926699a0da7095ff83b2106af2359
+size 471262

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_local_shared.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8467ffced719677e4e2563ac41cadac5b55b20315a7b8c0fc866484c46485822
+size 230218752

MOSS-TTS-Nano-cantophon-ONNX/moss_tts_prefill.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22844a9cd0bd48c61006301d1eb75d6a78085b3e038f405fb990b2994adb78b2
+size 283305

MOSS-TTS-Nano-cantophon-ONNX/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c353ee1479b536bf414c1b247f5542b6607fb8ae91320e5af1781fee200fddff
+size 470897

MOSS-TTS-Nano-cantophon-ONNX/tts_browser_onnx_meta.json

@@ -0,0 +1,186 @@
+{
+  "format_version": 1,
+  "checkpoint_path": "checkpoint-last",
+  "files": {
+    "prefill": "moss_tts_prefill.onnx",
+    "decode_step": "moss_tts_decode_step.onnx",
+    "local_decoder": "moss_tts_local_decoder.onnx",
+    "local_cached_step": "moss_tts_local_cached_step.onnx",
+    "local_fixed_sampled_frame": "moss_tts_local_fixed_sampled_frame.onnx"
+  },
+  "external_data_files": {
+    "moss_tts_prefill.onnx": [
+      "moss_tts_global_shared.data"
+    ],
+    "moss_tts_decode_step.onnx": [
+      "moss_tts_global_shared.data"
+    ],
+    "moss_tts_local_decoder.onnx": [
+      "moss_tts_local_shared.data"
+    ],
+    "moss_tts_local_cached_step.onnx": [
+      "moss_tts_local_shared.data"
+    ],
+    "moss_tts_local_fixed_sampled_frame.onnx": [
+      "moss_tts_local_shared.data"
+    ]
+  },
+  "model_config": {
+    "n_vq": 16,
+    "row_width": 17,
+    "hidden_size": 768,
+    "global_layers": 12,
+    "global_heads": 12,
+    "head_dim": 64,
+    "local_layers": 1,
+    "local_heads": 12,
+    "local_head_dim": 64,
+    "vocab_size": 16472,
+    "audio_codebook_sizes": [
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024,
+      1024
+    ],
+    "audio_pad_token_id": 1024,
+    "pad_token_id": 3,
+    "im_start_token_id": 4,
+    "im_end_token_id": 5,
+    "audio_start_token_id": 6,
+    "audio_end_token_id": 7,
+    "audio_user_slot_token_id": 8,
+    "audio_assistant_slot_token_id": 9
+  },
+  "onnx": {
+    "opset": 17,
+    "prefill_output_names": [
+      "global_hidden",
+      "present_key_0",
+      "present_value_0",
+      "present_key_1",
+      "present_value_1",
+      "present_key_2",
+      "present_value_2",
+      "present_key_3",
+      "present_value_3",
+      "present_key_4",
+      "present_value_4",
+      "present_key_5",
+      "present_value_5",
+      "present_key_6",
+      "present_value_6",
+      "present_key_7",
+      "present_value_7",
+      "present_key_8",
+      "present_value_8",
+      "present_key_9",
+      "present_value_9",
+      "present_key_10",
+      "present_value_10",
+      "present_key_11",
+      "present_value_11"
+    ],
+    "decode_input_names": [
+      "input_ids",
+      "past_valid_lengths",
+      "past_key_0",
+      "past_value_0",
+      "past_key_1",
+      "past_value_1",
+      "past_key_2",
+      "past_value_2",
+      "past_key_3",
+      "past_value_3",
+      "past_key_4",
+      "past_value_4",
+      "past_key_5",
+      "past_value_5",
+      "past_key_6",
+      "past_value_6",
+      "past_key_7",
+      "past_value_7",
+      "past_key_8",
+      "past_value_8",
+      "past_key_9",
+      "past_value_9",
+      "past_key_10",
+      "past_value_10",
+      "past_key_11",
+      "past_value_11"
+    ],
+    "decode_output_names": [
+      "global_hidden",
+      "present_key_0",
+      "present_value_0",
+      "present_key_1",
+      "present_value_1",
+      "present_key_2",
+      "present_value_2",
+      "present_key_3",
+      "present_value_3",
+      "present_key_4",
+      "present_value_4",
+      "present_key_5",
+      "present_value_5",
+      "present_key_6",
+      "present_value_6",
+      "present_key_7",
+      "present_value_7",
+      "present_key_8",
+      "present_value_8",
+      "present_key_9",
+      "present_value_9",
+      "present_key_10",
+      "present_value_10",
+      "present_key_11",
+      "present_value_11"
+    ],
+    "local_cached_input_names": [
+      "global_hidden",
+      "text_token_id",
+      "audio_token_id",
+      "channel_index",
+      "step_type",
+      "past_valid_lengths",
+      "local_past_key_0",
+      "local_past_value_0"
+    ],
+    "local_cached_output_names": [
+      "text_logits",
+      "audio_logits",
+      "local_present_key_0",
+      "local_present_value_0"
+    ],
+    "local_fixed_sampled_frame_input_names": [
+      "global_hidden",
+      "repetition_seen_mask",
+      "assistant_random_u",
+      "audio_random_u"
+    ],
+    "local_fixed_sampled_frame_output_names": [
+      "should_continue",
+      "frame_token_ids"
+    ],
+    "fixed_sampled_frame_constants": {
+      "text_temperature": 1.0,
+      "text_top_p": 1.0,
+      "text_top_k": 50,
+      "audio_temperature": 0.8,
+      "audio_top_p": 0.95,
+      "audio_top_k": 25,
+      "audio_repetition_penalty": 1.2
+    }
+  }
+}

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+language:
+- yue
+- en
+base_model: OpenMOSS/MOSS-TTS-Nano
+pipeline_tag: text-to-speech
+tags:
+- text-to-speech
+- cantonese
+- jyutping
+- onnx
+- speech
+---
+
+# canto-tts-nano-v1
+
+Open-source **Hong Kong Cantonese** text-to-speech, fine-tuned from
+[MOSS-TTS-Nano](https://github.com/OpenMOSS/MOSS-TTS) (0.1B params, GPT-2 backbone, Apache-2.0).
+CPU-first — runs via ONNX Runtime, no GPU required.
+
+This repo ships the **ONNX export** consumed by the
+[`canto-tts`](https://github.com/typangaa/canto-tts) Python SDK. It bundles the fine-tuned TTS
+graphs, the stock (unmodified) OpenMOSS audio-codec ONNX graphs, and one baked default voice.
+
+## Why a dedicated Cantonese fine-tune
+
+MOSS-TTS-Nano's base pretraining is Mandarin-centric — feeding it raw Hanzi produces Mandarin-accented
+output. This fine-tune instead feeds **jyutping phoneme tokens** (onset/rime/tone) for Chinese
+characters, while leaving English words as plain orthography (the base model's multilingual English
+prior is already good) — this is what actually yields Cantonese output with natural English
+code-switching. Text→jyutping conversion is handled upstream by
+[`canto-hk-g2p`](https://github.com/typangaa/canto-hk-g2p); this checkpoint only consumes phoneme
+tokens, it does not do grapheme-to-phoneme itself.
+
+## Usage
+
+```bash
+pip install canto-tts   # see https://github.com/typangaa/canto-tts for current install instructions
+```
+
+```python
+from canto_tts import CantoTTS
+
+tts = CantoTTS()  # auto-downloads this repo via huggingface_hub, cached under ~/.cache/huggingface
+tts.synthesize("多謝晒，今日天氣幾好。", "hello.wav")
+
+# English code-switching
+tts.synthesize("我哋一齊去 IFC food court 食飯。", "codeswitching.wav")
+```
+
+Advanced / no-SDK usage: `browser_poc_manifest.json` describes the ONNX graph layout (prefill/decode
+steps for the TTS local+global transformer, plus the codec encode/decode graphs) and carries the
+baked default-voice `audio_codes` — see `canto_tts.backends.onnx_backend.OnnxBackend` in the SDK repo
+for the reference ONNX Runtime session-wiring implementation.
+
+## Gate results (N=5 repeats, Qwen3-ASR-1.7B judge)
+
+| Gate | Set | Result | Threshold | Status |
+|---|---|---|---|---|
+| CER | golden_prompts (100 Cantonese sentences) | **11.82%** | < 15% | ✅ |
+| Tone accuracy | same | **84.22%** | ≥ 70% | ✅ |
+| Code-switch CER | same | **13.87%** | < 15% | ✅ |
+| Pure-English CER | 20 English-only sentences | **9.7%** | < 15% | ✅ |
+| Voice-clone CER (zero-shot) | 6 speakers × 5 targets | **10.2%** | ≤ 11% | ✅ |
+
+Full lineage, methodology, and paired-bootstrap significance notes: see the
+[GitHub repo](https://github.com/typangaa/canto-tts).
+
+## Default voice
+
+The single baked default voice is **this checkpoint's own unconditional (`mode="continuation"`)
+output** — i.e. self-generated speech, not a copy of any identifiable real person's recording and not
+borrowed from another project's demo asset. This sidesteps voice-likeness/rights questions entirely
+for the shipped default. There is currently no runtime voice selection in the ONNX bundle (one baked
+voice only) — multi-voice picking is planned for a future release via the underlying checkpoint's
+native zero-shot voice-cloning path, not this static ONNX export.
+
+## Known limitations
+
+- **Single default voice** — no voice selection or cloning in this ONNX bundle.
+- **Cantonese + English code-switching only** — Mandarin capability was intentionally not preserved
+  (the phoneme fine-tune overrides the base model's Mandarin reading prior for Chinese characters by
+  design).
+- No explicit style/emotion/gender control at inference — the training schema's control fields are
+  fixed to a neutral default for this checkpoint.
+
+## License
+
+Apache-2.0, inherited from [MOSS-TTS-Nano](https://github.com/OpenMOSS/MOSS-TTS) (OpenMOSS). The
+audio codec graphs (`MOSS-Audio-Tokenizer-Nano-ONNX/`) are the stock, unmodified OpenMOSS codec,
+included here only for convenience so the SDK has a single download.
+
+Training data is privately sourced and **not released** (copyright) — only these weights are public.

added_tokens.json

@@ -0,0 +1,90 @@
+{
+  "<o-b>": 16384,
+  "<o-c>": 16385,
+  "<o-d>": 16386,
+  "<o-f>": 16387,
+  "<o-g>": 16388,
+  "<o-gw>": 16389,
+  "<o-h>": 16390,
+  "<o-j>": 16391,
+  "<o-k>": 16392,
+  "<o-kw>": 16393,
+  "<o-l>": 16394,
+  "<o-m>": 16395,
+  "<o-n>": 16396,
+  "<o-ng>": 16397,
+  "<o-p>": 16398,
+  "<o-s>": 16399,
+  "<o-t>": 16400,
+  "<o-w>": 16401,
+  "<o-z>": 16402,
+  "<pause-long>": 16471,
+  "<pause-short>": 16470,
+  "<r-a>": 16403,
+  "<r-aa>": 16404,
+  "<r-aai>": 16405,
+  "<r-aak>": 16406,
+  "<r-aam>": 16407,
+  "<r-aan>": 16408,
+  "<r-aang>": 16409,
+  "<r-aap>": 16410,
+  "<r-aat>": 16411,
+  "<r-aau>": 16412,
+  "<r-ai>": 16413,
+  "<r-ak>": 16414,
+  "<r-am>": 16415,
+  "<r-an>": 16416,
+  "<r-ang>": 16417,
+  "<r-ap>": 16418,
+  "<r-at>": 16419,
+  "<r-au>": 16420,
+  "<r-e>": 16421,
+  "<r-ei>": 16422,
+  "<r-ek>": 16423,
+  "<r-em>": 16424,
+  "<r-eng>": 16425,
+  "<r-eoi>": 16426,
+  "<r-eon>": 16427,
+  "<r-eot>": 16428,
+  "<r-ep>": 16429,
+  "<r-et>": 16430,
+  "<r-eu>": 16431,
+  "<r-i>": 16432,
+  "<r-ik>": 16433,
+  "<r-im>": 16434,
+  "<r-in>": 16435,
+  "<r-ing>": 16436,
+  "<r-ip>": 16437,
+  "<r-it>": 16438,
+  "<r-iu>": 16439,
+  "<r-m>": 16440,
+  "<r-ng>": 16441,
+  "<r-o>": 16442,
+  "<r-oe>": 16443,
+  "<r-oek>": 16444,
+  "<r-oeng>": 16445,
+  "<r-oet>": 16446,
+  "<r-oi>": 16447,
+  "<r-ok>": 16448,
+  "<r-om>": 16449,
+  "<r-on>": 16450,
+  "<r-ong>": 16451,
+  "<r-op>": 16452,
+  "<r-ot>": 16453,
+  "<r-ou>": 16454,
+  "<r-u>": 16455,
+  "<r-ui>": 16456,
+  "<r-uk>": 16457,
+  "<r-un>": 16458,
+  "<r-ung>": 16459,
+  "<r-ut>": 16460,
+  "<r-yu>": 16461,
+  "<r-yun>": 16462,
+  "<r-yut>": 16463,
+  "<t1>": 16464,
+  "<t2>": 16465,
+  "<t3>": 16466,
+  "<t4>": 16467,
+  "<t5>": 16468,
+  "<t6>": 16469
+}

browser_poc_manifest.json

@@ -0,0 +1,909 @@
+{
+  "format_version": 1,
+  "model_files": {
+    "tts_meta": "MOSS-TTS-Nano-cantophon-ONNX/tts_browser_onnx_meta.json",
+    "codec_meta": "MOSS-Audio-Tokenizer-Nano-ONNX/codec_browser_onnx_meta.json",
+    "tokenizer_model": "tokenizer.model",
+    "added_tokens": "added_tokens.json"
+  },
+  "tts_config": {
+    "n_vq": 16,
+    "audio_pad_token_id": 1024,
+    "audio_start_token_id": 6,
+    "audio_end_token_id": 7,
+    "audio_user_slot_token_id": 8,
+    "audio_assistant_slot_token_id": 9
+  },
+  "prompt_templates": {
+    "user_prompt_prefix_token_ids": [
+      4,
+      600,
+      289,
+      10356,
+      13,
+      10356,
+      10425,
+      1860,
+      4546,
+      12907,
+      10363,
+      13325,
+      11492
+    ],
+    "user_prompt_after_reference_token_ids": [
+      10356,
+      10425,
+      3965,
+      7738,
+      11492,
+      505,
+      587,
+      10356,
+      10425,
+      352,
+      500,
+      856,
+      11492,
+      505,
+      587,
+      10356,
+      10425,
+      2128,
+      1247,
+      594,
+      11492,
+      505,
+      587,
+      10356,
+      10425,
+      348,
+      909,
+      561,
+      3648,
+      11492,
+      505,
+      587,
+      10356,
+      10425,
+      2818,
+      1305,
+      355,
+      348,
+      909,
+      11492,
+      505,
+      587,
+      10356,
+      10425,
+      484,
+      339,
+      10367,
+      783,
+      11492,
+      505,
+      587,
+      10356,
+      10425,
+      2427,
+      980,
+      11492
+    ],
+    "assistant_prompt_prefix_token_ids": [
+      10356,
+      14,
+      5,
+      4,
+      8165,
+      430
+    ]
+  },
+  "generation_defaults": {
+    "max_new_frames": 375,
+    "do_sample": true,
+    "sample_mode": "fixed",
+    "text_temperature": 0.9,
+    "text_top_p": 1.0,
+    "text_top_k": 50,
+    "audio_temperature": 0.9,
+    "audio_top_p": 0.9,
+    "audio_top_k": 25,
+    "audio_repetition_penalty": 1.0
+  },
+  "default_voice": {
+    "voice": "male_default",
+    "prompt_audio_codes": [
+      [
+        461,
+        460,
+        54,
+        81,
+        322,
+        964,
+        804,
+        115,
+        92,
+        681,
+        701,
+        616,
+        65,
+        922,
+        877,
+        176
+      ],
+      [
+        946,
+        100,
+        796,
+        509,
+        848,
+        465,
+        432,
+        855,
+        381,
+        847,
+        538,
+        442,
+        894,
+        896,
+        599,
+        53
+      ],
+      [
+        850,
+        390,
+        641,
+        645,
+        583,
+        172,
+        870,
+        36,
+        437,
+        114,
+        525,
+        419,
+        569,
+        328,
+        645,
+        38
+      ],
+      [
+        1011,
+        132,
+        222,
+        904,
+        304,
+        854,
+        487,
+        103,
+        72,
+        567,
+        996,
+        151,
+        932,
+        105,
+        496,
+        984
+      ],
+      [
+        743,
+        315,
+        548,
+        387,
+        432,
+        202,
+        555,
+        267,
+        88,
+        460,
+        316,
+        633,
+        16,
+        769,
+        539,
+        611
+      ],
+      [
+        677,
+        710,
+        804,
+        762,
+        218,
+        624,
+        968,
+        454,
+        830,
+        726,
+        398,
+        312,
+        638,
+        520,
+        189,
+        522
+      ],
+      [
+        684,
+        815,
+        157,
+        988,
+        640,
+        273,
+        627,
+        198,
+        148,
+        922,
+        860,
+        620,
+        786,
+        259,
+        833,
+        78
+      ],
+      [
+        985,
+        491,
+        413,
+        847,
+        934,
+        634,
+        43,
+        560,
+        533,
+        644,
+        739,
+        72,
+        76,
+        254,
+        89,
+        344
+      ],
+      [
+        623,
+        880,
+        222,
+        1004,
+        937,
+        915,
+        291,
+        922,
+        590,
+        952,
+        429,
+        566,
+        524,
+        30,
+        251,
+        349
+      ],
+      [
+        815,
+        70,
+        727,
+        721,
+        923,
+        526,
+        960,
+        254,
+        914,
+        922,
+        656,
+        736,
+        755,
+        782,
+        839,
+        952
+      ],
+      [
+        273,
+        275,
+        647,
+        673,
+        164,
+        705,
+        388,
+        113,
+        980,
+        175,
+        978,
+        965,
+        671,
+        131,
+        91,
+        622
+      ],
+      [
+        273,
+        266,
+        128,
+        862,
+        806,
+        791,
+        341,
+        391,
+        330,
+        491,
+        257,
+        16,
+        596,
+        7,
+        193,
+        77
+      ],
+      [
+        262,
+        94,
+        335,
+        472,
+        466,
+        867,
+        496,
+        799,
+        940,
+        49,
+        426,
+        97,
+        86,
+        833,
+        34,
+        975
+      ],
+      [
+        642,
+        311,
+        725,
+        1020,
+        170,
+        926,
+        439,
+        691,
+        353,
+        759,
+        404,
+        847,
+        73,
+        24,
+        593,
+        227
+      ],
+      [
+        642,
+        913,
+        749,
+        526,
+        208,
+        161,
+        479,
+        123,
+        419,
+        0,
+        444,
+        51,
+        246,
+        264,
+        64,
+        155
+      ],
+      [
+        642,
+        700,
+        360,
+        178,
+        986,
+        195,
+        869,
+        121,
+        170,
+        232,
+        413,
+        1004,
+        922,
+        612,
+        426,
+        612
+      ],
+      [
+        642,
+        13,
+        448,
+        252,
+        513,
+        439,
+        967,
+        481,
+        668,
+        968,
+        860,
+        234,
+        721,
+        177,
+        363,
+        476
+      ],
+      [
+        808,
+        564,
+        231,
+        667,
+        108,
+        782,
+        338,
+        82,
+        340,
+        549,
+        856,
+        337,
+        725,
+        836,
+        17,
+        19
+      ],
+      [
+        845,
+        239,
+        943,
+        891,
+        807,
+        350,
+        98,
+        408,
+        708,
+        858,
+        378,
+        230,
+        741,
+        145,
+        651,
+        605
+      ],
+      [
+        412,
+        119,
+        134,
+        604,
+        543,
+        857,
+        1009,
+        93,
+        891,
+        375,
+        860,
+        469,
+        391,
+        470,
+        853,
+        311
+      ],
+      [
+        175,
+        159,
+        521,
+        657,
+        254,
+        706,
+        109,
+        828,
+        985,
+        843,
+        116,
+        536,
+        923,
+        584,
+        144,
+        673
+      ],
+      [
+        916,
+        477,
+        948,
+        145,
+        534,
+        534,
+        260,
+        914,
+        87,
+        918,
+        140,
+        553,
+        682,
+        230,
+        416,
+        586
+      ],
+      [
+        957,
+        745,
+        203,
+        836,
+        865,
+        684,
+        5,
+        905,
+        658,
+        966,
+        759,
+        258,
+        453,
+        394,
+        164,
+        764
+      ],
+      [
+        972,
+        121,
+        967,
+        607,
+        843,
+        948,
+        722,
+        612,
+        590,
+        108,
+        984,
+        958,
+        19,
+        28,
+        590,
+        138
+      ],
+      [
+        1020,
+        369,
+        654,
+        932,
+        996,
+        245,
+        894,
+        669,
+        266,
+        111,
+        770,
+        310,
+        603,
+        436,
+        201,
+        659
+      ],
+      [
+        623,
+        949,
+        4,
+        76,
+        706,
+        1017,
+        670,
+        329,
+        21,
+        379,
+        727,
+        619,
+        888,
+        246,
+        181,
+        390
+      ],
+      [
+        579,
+        544,
+        1015,
+        823,
+        446,
+        359,
+        205,
+        67,
+        788,
+        12,
+        711,
+        610,
+        284,
+        653,
+        180,
+        976
+      ],
+      [
+        819,
+        205,
+        794,
+        567,
+        561,
+        914,
+        813,
+        769,
+        251,
+        995,
+        162,
+        122,
+        713,
+        506,
+        734,
+        344
+      ],
+      [
+        689,
+        940,
+        647,
+        1017,
+        845,
+        352,
+        731,
+        643,
+        838,
+        660,
+        505,
+        939,
+        645,
+        884,
+        169,
+        796
+      ],
+      [
+        909,
+        383,
+        522,
+        397,
+        1008,
+        51,
+        456,
+        412,
+        826,
+        455,
+        972,
+        702,
+        786,
+        254,
+        408,
+        976
+      ],
+      [
+        167,
+        427,
+        54,
+        363,
+        358,
+        102,
+        611,
+        669,
+        978,
+        774,
+        167,
+        274,
+        371,
+        879,
+        64,
+        102
+      ],
+      [
+        670,
+        666,
+        485,
+        230,
+        1002,
+        523,
+        110,
+        136,
+        356,
+        192,
+        860,
+        773,
+        629,
+        518,
+        556,
+        274
+      ],
+      [
+        199,
+        666,
+        371,
+        148,
+        205,
+        58,
+        465,
+        768,
+        956,
+        944,
+        421,
+        828,
+        460,
+        464,
+        662,
+        477
+      ],
+      [
+        199,
+        666,
+        716,
+        524,
+        927,
+        564,
+        333,
+        516,
+        561,
+        325,
+        935,
+        986,
+        837,
+        357,
+        947,
+        879
+      ],
+      [
+        356,
+        449,
+        770,
+        713,
+        707,
+        948,
+        153,
+        466,
+        216,
+        631,
+        395,
+        894,
+        300,
+        922,
+        873,
+        733
+      ],
+      [
+        916,
+        104,
+        336,
+        695,
+        707,
+        826,
+        161,
+        531,
+        1001,
+        482,
+        990,
+        654,
+        523,
+        94,
+        378,
+        222
+      ],
+      [
+        872,
+        837,
+        89,
+        608,
+        238,
+        492,
+        298,
+        69,
+        312,
+        600,
+        727,
+        44,
+        135,
+        21,
+        624,
+        688
+      ],
+      [
+        318,
+        868,
+        909,
+        1015,
+        553,
+        288,
+        404,
+        31,
+        240,
+        769,
+        371,
+        113,
+        806,
+        822,
+        388,
+        834
+      ],
+      [
+        684,
+        859,
+        757,
+        57,
+        645,
+        119,
+        373,
+        293,
+        1012,
+        706,
+        118,
+        329,
+        529,
+        240,
+        180,
+        781
+      ],
+      [
+        738,
+        469,
+        553,
+        216,
+        219,
+        661,
+        206,
+        579,
+        763,
+        766,
+        488,
+        555,
+        623,
+        890,
+        319,
+        672
+      ],
+      [
+        925,
+        469,
+        553,
+        719,
+        866,
+        702,
+        389,
+        616,
+        98,
+        106,
+        753,
+        386,
+        307,
+        852,
+        433,
+        956
+      ],
+      [
+        623,
+        893,
+        615,
+        538,
+        658,
+        948,
+        740,
+        636,
+        146,
+        980,
+        17,
+        502,
+        398,
+        376,
+        214,
+        673
+      ],
+      [
+        664,
+        144,
+        114,
+        719,
+        710,
+        972,
+        766,
+        932,
+        225,
+        544,
+        88,
+        249,
+        685,
+        241,
+        738,
+        38
+      ],
+      [
+        670,
+        666,
+        42,
+        252,
+        448,
+        580,
+        852,
+        65,
+        144,
+        1,
+        936,
+        895,
+        445,
+        229,
+        215,
+        858
+      ]
+    ]
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c353ee1479b536bf414c1b247f5542b6607fb8ae91320e5af1781fee200fddff
+size 470897