mirror: soar ← rednote-hilab/dots.tts-soar

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 base/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+soar/tokenizer.json filter=lfs diff=lfs merge=lfs -text

soar/.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

soar/README.md

@@ -0,0 +1,181 @@
+---
+license: apache-2.0
+pipeline_tag: text-to-speech
+tags:
+  - text-to-speech
+  - tts
+  - audio
+  - speech-synthesis
+  - voice-cloning
+  - autoregressive
+  - flow-matching
+  - post-trained
+library_name: dots_tts
+base_model: rednote-hilab/dots.tts-base
+---
+
+# dots.tts-soar
+
+<p align="left">
+  <a href="https://github.com/rednote-hilab/dots.tts"><img src="https://img.shields.io/badge/GitHub-rednote--hilab%2Fdots.tts-blue?logo=github" alt="GitHub"></a>
+  <a href="https://huggingface.co/spaces/rednote-hilab/dots.tts"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Spaces-Playground-orange" alt="Playground"></a>
+  <a href="https://rednote-hilab.github.io/dots.tts-demo/"><img src="https://img.shields.io/badge/Demo%20Page-Live-red" alt="Demo Page"></a>
+</p>
+
+**dots.tts** is a **2B-parameter fully continuous, end-to-end autoregressive (AR) text-to-speech system**. The backbone pairs a semantic encoder, an LLM, and an autoregressive flow-matching acoustic head over a 48 kHz AudioVAE — no discrete codec tokens anywhere in the pipeline.
+
+This repository hosts **`dots.tts-soar`** — the pretrained backbone further refined with **Self-corrective Alignment (SCA)**, a reward-free flow-matching-native post-training stage. SCA pushes the model to the **highest zero-shot fidelity and speaker similarity** of the three releases and is the **recommended default for production zero-shot voice cloning**.
+
+<table>
+  <tr>
+    <td align="left" valign="middle"><a href="https://huggingface.co/rednote-hilab/dots.tts-base"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-dots.tts--base-yellow" alt="dots.tts-base"></a></td>
+    <td>Pretrain (~1.5M h). Fine-tuning, full CFG / NFE control.</td>
+  </tr>
+  <tr>
+    <td align="left" valign="middle"><a href="https://huggingface.co/rednote-hilab/dots.tts-soar"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-dots.tts--soar-yellow" alt="dots.tts-soar"></a></td>
+    <td>← <em>you are here</em> — + Self-corrective Alignment. <strong>Highest zero-shot fidelity and speaker similarity</strong>; also recommended for fine-tuning.</td>
+  </tr>
+  <tr>
+    <td align="left" valign="middle"><a href="https://huggingface.co/rednote-hilab/dots.tts-mf"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-dots.tts--mf-yellow" alt="dots.tts-mf"></a></td>
+    <td>+ MeanFlow distillation. Few-step inference (NFE = 4), low latency.</td>
+  </tr>
+</table>
+
+---
+
+## Quick Start
+
+### Installation
+
+```bash
+conda create -n dots_tts python=3.10 -y
+conda activate dots_tts
+
+python -m pip install --upgrade pip
+python -m pip install "git+https://github.com/rednote-hilab/dots.tts.git" \
+  -c "https://raw.githubusercontent.com/rednote-hilab/dots.tts/main/constraints/recommended.txt"
+```
+
+### CLI
+
+```bash
+# Continuation voice cloning (reference audio + transcript) — recommended
+dots.tts \
+  --model-name-or-path rednote-hilab/dots.tts-soar \
+  --text "Hello, this is a zero-shot voice cloning demonstration." \
+  --prompt-audio /path/to/reference.wav \
+  --prompt-text "The exact transcript of the reference audio." \
+  --output clone.wav
+```
+
+### Python API
+
+```python
+from dots_tts.runtime import DotsTtsRuntime
+import soundfile as sf
+
+runtime = DotsTtsRuntime.from_pretrained(
+    "rednote-hilab/dots.tts-soar",
+    precision="bfloat16",
+)
+
+result = runtime.generate(
+    text="Hello, this is a quick speech synthesis test.",
+    prompt_audio_path="/path/to/reference.wav",
+    prompt_text="The exact transcript of the reference audio.",
+    num_steps=10,
+    guidance_scale=1.2,
+)
+
+sf.write("output.wav", result["audio"].float().cpu().squeeze().numpy(), result["sample_rate"])
+```
+
+### Recommended sampling settings
+
+| Flag | Recommended | Notes |
+|---|---:|---|
+| `--num-steps` | `10`–`32` | Flow-matching sampling steps; higher = better quality, slower |
+| `--guidance-scale` | `1.2` (default) | Standard CFG; SCA already tightens text and timbre adherence so small CFG suffices |
+
+### Fine-tuning
+
+Both `dots.tts-base` and `dots.tts-soar` are valid fine-tuning starting points. Pick `dots.tts-soar` when you want to inherit its tightened text/timbre alignment on top of the pretrained backbone. See the [training script](https://github.com/rednote-hilab/dots.tts/blob/main/scripts/train_dots_tts.py) and [smoke config](https://github.com/rednote-hilab/dots.tts/blob/main/configs/dots_tts.yaml) in the source repository:
+
+```bash
+accelerate launch scripts/train_dots_tts.py --config configs/dots_tts.yaml
+```
+
+---
+
+## Architecture
+
+A frozen **AudioVAE** encodes 48 kHz mono waveform into a continuous latent and decodes it back via a BigVGAN-style causal decoder. An **autoregressive backbone** predicts that latent one patch at a time:
+
+- **Semantic encoder** — re-encodes each newly generated VAE patch into a compact embedding for the LLM, stripping high-variance acoustic detail.
+- **LLM** — initialized from **Qwen2.5-1.5B-Base**, consumes BPE text directly (no phonemes), emits one hidden state per audio step.
+- **AR flow-matching head** — a DiT that conditions on the LLM hidden state and the AR prefix to denoise the next VAE patch, with a frozen CAM++ speaker x-vector as side input.
+
+**Self-corrective Alignment** is a reward-free, flow-matching-native post-training stage applied on top of `dots.tts-base`. It improves text and speaker adherence without changing inference cost or sampling schedule.
+
+---
+
+## Performance — `dots.tts-soar`
+
+### Seed-TTS-Eval — **state-of-the-art average SIM (79.2)**
+
+| Model | Params | test-en WER↓ / SIM↑ | test-zh WER↓ / SIM↑ | test-zh-hard WER↓ / SIM↑ | **Avg WER↓ / SIM↑** |
+|---|---:|:---:|:---:|:---:|:---:|
+| Seed-TTS | — | 2.25 / 76.2 | 1.12 / 79.6 | 7.59 / 77.6 | 3.65 / 77.8 |
+| Qwen3-TTS | 1.7B | **1.23** / 71.7 | 1.22 / 77.0 | 6.76 / 74.8 | 3.07 / 74.5 |
+| VoxCPM 2 | 2B | 1.84 / 75.3 | 0.97 / 79.5 | 8.13 / 75.3 | 3.65 / 76.7 |
+| dots.tts-base | 2B | 1.34 / 76.8 | 0.96 / 80.5 | **6.46** / 79.2 | **2.92** / 78.8 |
+| **dots.tts-soar** | **2B** | 1.30 / **77.1** | **0.94** / **81.0** | 6.60 / **79.5** | 2.95 / **79.2** |
+
+### MiniMax Multilingual — **highest average SIM (83.9) across 24 languages**
+
+| Model | Avg WER↓ | Avg SIM↑ |
+|---|:---:|:---:|
+| MiniMax | **2.8** | 76.6 |
+| Fish-Audio S2 | 3.7 | 78.0 |
+| VoxCPM 2 | 5.7 | 82.3 |
+| dots.tts-base | 6.6 | 83.5 |
+| **dots.tts-soar** | 6.8 | **83.9** |
+
+### CV3-Eval — **leads both cross-lingual SIM subsets**
+
+| Model | en→zh SIM↑ | zh→en SIM↑ |
+|---|:---:|:---:|
+| CosyVoice 3 (1.5B) | 66.9 | 66.4 |
+| dots.tts-base | 74.6 | 71.9 |
+| **dots.tts-soar** | **75.0** | **72.8** |
+
+### EmergentTTS-Eval — **top Syntactic Complexity in the table (65.7%)**
+
+On head-to-head judging vs. `gpt-4o-mini-tts`, `dots.tts-soar` posts **65.7% on Syntactic Complexity — above every closed-source system listed**, while keeping competitive Emotions / Questions scores.
+
+See the [project README](https://github.com/rednote-hilab/dots.tts#-performance) for full benchmark tables.
+
+---
+
+## Risks and Limitations
+
+- **Misuse risk.** High-fidelity zero-shot voice cloning can produce highly realistic synthetic speech. This checkpoint is intended for research and authorized deployment. Do **not** use it for impersonation, fraud, or disinformation. Combine downstream use with consent-aware reference-audio policies, robust synthetic-speech detection, and content watermarking. Clearly mark AI-generated audio.
+- **Low-resource WER gap.** A BPE backbone inherits the text LLM's language coverage at the cost of a higher data appetite. On script-divergent and under-represented languages (Arabic, Hindi, Turkish, Vietnamese) WER is higher than on high-resource languages; speaker similarity is preserved.
+- **Speech-heavy training.** The backbone is trained on a speech-heavy mixture. Singing and unified speech + sound generation are not covered.
+
+---
+
+## Citation
+
+```bibtex
+@article{dotstts2026,
+  title   = {dots.tts Technical Report},
+  author  = {dots.tts Team},
+  journal = {arXiv preprint},
+  year    = {2026},
+}
+```
+
+## License
+
+Released under [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0).

soar/added_tokens.json

@@ -0,0 +1,31 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|audio_comp_end|>": 151667,
+  "<|audio_comp_span|>": 151666,
+  "<|audio_comp_start|>": 151665,
+  "<|audio_gen_end|>": 151670,
+  "<|audio_gen_span|>": 151669,
+  "<|audio_gen_start|>": 151668,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|text_cond_end|>": 151671,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

soar/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

soar/config.json

@@ -0,0 +1,113 @@
+{
+  "model_type": "dots_tts",
+  "latent_dim": 128,
+  "patch_size": 4,
+  "cfg_droprate": 0.2,
+  "PatchEncoder": {
+    "num_layers": 24,
+    "num_heads": 16,
+    "hidden_size": 1024,
+    "ffn_hidden_size": 4096,
+    "modulation": false,
+    "qkv_bias": false,
+    "qk_norm": true,
+    "attn_dropout": 0.0,
+    "dropout": 0.1,
+    "norm_layer": "RMSNorm",
+    "alibi_bias": false,
+    "rotary_bias": true,
+    "rotary_theta": 10000.0,
+    "input_dim": 128,
+    "causal": true
+  },
+  "DiT": {
+    "num_layers": 18,
+    "num_heads": 16,
+    "hidden_size": 1024,
+    "ffn_hidden_size": 4096,
+    "modulation": true,
+    "qkv_bias": false,
+    "qk_norm": true,
+    "attn_dropout": 0.0,
+    "dropout": 0.0,
+    "norm_layer": "RMSNorm",
+    "alibi_bias": false,
+    "rotary_bias": true,
+    "rotary_theta": 10000.0
+  },
+  "vocoder": {
+    "sample_rate": 48000,
+    "upsample_rates": [
+      10,
+      6,
+      4,
+      2,
+      2,
+      2
+    ],
+    "upsample_kernel_sizes": [
+      20,
+      12,
+      8,
+      4,
+      4,
+      4
+    ],
+    "upsample_initial_channel": 1536,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "downsample_rates": [
+      2,
+      2,
+      2,
+      4,
+      6,
+      10
+    ],
+    "downsample_channels": [
+      12,
+      24,
+      48,
+      96,
+      192,
+      384,
+      768
+    ],
+    "activation": "snakebeta",
+    "snake_logscale": true,
+    "latent_dim": 128,
+    "causal": true,
+    "mi_num_layers": 4,
+    "causal_encoder": true,
+    "use_bias_at_final": false,
+    "use_tanh_at_final": false
+  },
+  "fm_sigma": 0.0,
+  "xvec_drop_rate": 0.2,
+  "campplus_embedding_size": 512,
+  "xvec_max_audio_seconds": 10.0,
+  "architectures": [
+    "DotsTTSForConditionalGeneration"
+  ]
+}

soar/latent_stats.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313b13af56d659ecf869d5f854508fcf823c8f957aefc6bc05244991abd6ffe1
+size 3197

soar/llm_config.json

@@ -0,0 +1,114 @@
+{
+  "vocab_size": 151672,
+  "max_position_embeddings": 131072,
+  "hidden_size": 1536,
+  "intermediate_size": 8960,
+  "num_hidden_layers": 28,
+  "num_attention_heads": 12,
+  "use_sliding_window": false,
+  "sliding_window": null,
+  "max_window_layers": 28,
+  "num_key_value_heads": 2,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "use_cache": true,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_dropout": 0.0,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "dtype": "bfloat16",
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "task_specific_params": null,
+  "problem_type": null,
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 151643,
+  "pad_token_id": null,
+  "eos_token_id": 151643,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "_name_or_path": "",
+  "transformers_version": "4.57.0",
+  "model_type": "qwen2",
+  "use_mrope": false,
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "output_attentions": false
+}

soar/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2787e6d4fe0b27ac33d28072abcadef53802c841bff037f3ee1f6bb5e1d3a2ce
+size 4396289197

soar/speaker_encoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf3861c9dee79e4db34bd0b8a4155e68bed27a7c6274e168bb6ee4fed191c85
+size 29150484

soar/special_tokens_map.json

@@ -0,0 +1,67 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|audio_comp_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|audio_comp_span|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|audio_comp_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|audio_gen_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|audio_gen_span|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|audio_gen_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|text_cond_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

soar/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16521f66774c7a4774e5303b7c8ec5c99830c0be5aef6c6edde3ca2a5e05dd0
+size 11423263

soar/tokenizer_config.json

@@ -0,0 +1,257 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|audio_comp_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|audio_comp_span|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|audio_comp_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|audio_gen_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|audio_gen_span|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_gen_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|text_cond_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|audio_comp_start|>",
+    "<|audio_comp_span|>",
+    "<|audio_comp_end|>",
+    "<|audio_gen_start|>",
+    "<|audio_gen_span|>",
+    "<|audio_gen_end|>",
+    "<|text_cond_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

soar/vocoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e45c08f480df67ac4c354b465355fcc7e2f6c8765263b6dfeddd1f4671c93d
+size 723585584