Upload model

.gitattributes

@@ -33,3 +33,4 @@ 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
+qwen0.6bemo4-merge/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+language:
+- en
+---
+## 👉🏻 IndexTTS2 👈🏻
+
+<center><h3>IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech</h3></center>
+
+
+<div align="center">
+  <a href='https://arxiv.org/abs/2506.21619'>
+    <img src='https://img.shields.io/badge/ArXiv-2506.21619-red?logo=arxiv'/>
+  </a>
+  <br/>
+  <a href='https://github.com/index-tts/index-tts'>
+    <img src='https://img.shields.io/badge/GitHub-Code-orange?logo=github'/>
+  </a>
+  <a href='https://index-tts.github.io/index-tts2.github.io/'>
+    <img src='https://img.shields.io/badge/GitHub-Demo-orange?logo=github'/>
+  </a>
+  <br/>
+  <!--a href='https://huggingface.co/spaces/IndexTeam/IndexTTS'>
+    <img src='https://img.shields.io/badge/HuggingFace-Demo-blue?logo=huggingface'/>
+  </a-->
+  <a href='https://huggingface.co/IndexTeam/IndexTTS-2'>
+    <img src='https://img.shields.io/badge/HuggingFace-Model-blue?logo=huggingface' />
+  </a>
+  <br/>
+  <!--a href='https://modelscope.cn/studios/IndexTeam/IndexTTS-Demo'>
+    <img src='https://img.shields.io/badge/ModelScope-Demo-purple?logo=modelscope'/>
+  </a-->
+  <a href='https://modelscope.cn/models/IndexTeam/IndexTTS-2'>
+    <img src='https://img.shields.io/badge/ModelScope-Model-purple?logo=modelscope'/>
+  </a>
+</div>
+
+
+## Acknowledge
+1. [tortoise-tts](https://github.com/neonbjb/tortoise-tts)
+2. [XTTSv2](https://github.com/coqui-ai/TTS)
+3. [BigVGAN](https://github.com/NVIDIA/BigVGAN)
+4. [wenet](https://github.com/wenet-e2e/wenet/tree/main)
+5. [icefall](https://github.com/k2-fsa/icefall)
+6. [maskgct](https://github.com/open-mmlab/Amphion/tree/main/models/tts/maskgct)
+7. [seed-vc](https://github.com/Plachtaa/seed-vc)
+
+
+## 📚 Citation
+
+🌟 If you find our work helpful, please leave us a star and cite our paper.
+
+
+IndexTTS2
+```
+@article{zhou2025indextts2,
+  title={IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech},
+  author={Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, Jingchen Shu},
+  journal={arXiv preprint arXiv:2506.21619},
+  year={2025}
+}
+```
+
+IndexTTS
+```
+@article{deng2025indextts,
+  title={IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System},
+  author={Wei Deng, Siyi Zhou, Jingchen Shu, Jinchao Wang, Lu Wang},
+  journal={arXiv preprint arXiv:2502.05512},
+  year={2025},
+  doi={10.48550/arXiv.2502.05512},
+  url={https://arxiv.org/abs/2502.05512}
+}
+```

bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a5ce8090d32da3642cc4f81fdc996376bc6dd3f4cd5e3d165f71120d9f2bc8
+size 475997

config.yaml

@@ -0,0 +1,120 @@
+dataset:
+    bpe_model: bpe.model
+    sample_rate: 24000
+    squeeze: false
+    mel:
+        sample_rate: 24000
+        n_fft: 1024
+        hop_length: 256
+        win_length: 1024
+        n_mels: 100
+        mel_fmin: 0
+        normalize: false
+
+gpt:
+    model_dim: 1280
+    max_mel_tokens: 1815
+    max_text_tokens: 600
+    heads: 20
+    use_mel_codes_as_input: true
+    mel_length_compression: 1024
+    layers: 24
+    number_text_tokens: 12000
+    number_mel_codes: 8194
+    start_mel_token: 8192
+    stop_mel_token: 8193
+    start_text_token: 0
+    stop_text_token: 1
+    train_solo_embeddings: false
+    condition_type: "conformer_perceiver"
+    condition_module:
+        output_size: 512
+        linear_units: 2048
+        attention_heads: 8
+        num_blocks: 6
+        input_layer: "conv2d2"
+        perceiver_mult: 2
+    emo_condition_module:
+        output_size: 512
+        linear_units: 1024
+        attention_heads: 4
+        num_blocks: 4
+        input_layer: "conv2d2"
+        perceiver_mult: 2
+
+semantic_codec:
+    codebook_size: 8192
+    hidden_size: 1024
+    codebook_dim: 8
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+
+s2mel:
+    preprocess_params:
+        sr: 22050
+        spect_params:
+            n_fft: 1024
+            win_length: 1024
+            hop_length: 256
+            n_mels: 80
+            fmin: 0
+            fmax: "None"
+
+    dit_type: "DiT"
+    reg_loss_type: "l1"
+    style_encoder:
+        dim: 192
+    length_regulator:
+        channels: 512
+        is_discrete: false
+        in_channels: 1024
+        content_codebook_size: 2048
+        sampling_ratios: [1, 1, 1, 1]
+        vector_quantize: false
+        n_codebooks: 1
+        quantizer_dropout: 0.0
+        f0_condition: false
+        n_f0_bins: 512
+    DiT:
+        hidden_dim: 512
+        num_heads: 8
+        depth: 13
+        class_dropout_prob: 0.1
+        block_size: 8192
+        in_channels: 80
+        style_condition: true
+        final_layer_type: 'wavenet'
+        target: 'mel'
+        content_dim: 512
+        content_codebook_size: 1024
+        content_type: 'discrete'
+        f0_condition: false
+        n_f0_bins: 512
+        content_codebooks: 1
+        is_causal: false
+        long_skip_connection: true
+        zero_prompt_speech_token: false
+        time_as_token: false
+        style_as_token: false
+        uvit_skip_connection: true
+        add_resblock_in_transformer: false
+    wavenet:
+        hidden_dim: 512
+        num_layers: 8
+        kernel_size: 5
+        dilation_rate: 1
+        p_dropout: 0.2
+        style_condition: true
+
+gpt_checkpoint: gpt.pth
+w2v_stat: wav2vec2bert_stats.pt
+s2mel_checkpoint: s2mel.pth
+emo_matrix: feat2.pt 
+spk_matrix: feat1.pt
+emo_num: [3, 17, 2, 8, 4, 5, 10, 24]
+qwen_emo_path: qwen0.6bemo4-merge/ 
+vocoder:
+    type: "bigvgan"
+    name: "nvidia/bigvgan_v2_22khz_80band_256x"
+version: 2.0

feat1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f219cb447d80216ba615666da2ff8d63ac544eee26657f3a7b278692bf7a67c4
+size 57170

feat2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4292e96dee535aea9a6206e9a0c856dd578dde9212acdb16dd3ada4d12bf80
+size 374866

gpt.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaaeb8b56328da81731dc540a85a7dee32eca9da28f174b05757cb651c602a4
+size 3484663079

qwen0.6bemo4-merge/Modelfile

@@ -0,0 +1,11 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}System: {{ .System }}<|endoftext|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}Human: {{ .Content }}<|endoftext|>
+Assistant:{{ else if eq .Role "assistant" }}{{ .Content }}<|endoftext|>
+{{ end }}{{ end }}"""
+
+PARAMETER stop "<|endoftext|>"
+PARAMETER num_ctx 4096

qwen0.6bemo4-merge/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen0.6bemo4-merge/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '
+' }}{% endif %}{% endfor %}

qwen0.6bemo4-merge/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen0.6bemo4-merge/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.1"
+}

qwen0.6bemo4-merge/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11293257a8df593c154a8ecd5fc039f3076de35411e35f06d41b471e136f6641
+size 1192135096

qwen0.6bemo4-merge/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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
+  }
+}

qwen0.6bemo4-merge/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

qwen0.6bemo4-merge/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

s2mel.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae1bb12017cbb47e7a5ce537fc82f40b6b1deb71acdb9b8f25686f32714b636
+size 1202198223

semantic_codec/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec947271175d8cad75ec37e83aa487e27c97a0f72a303393772da5ffa84bddf2
+size 177183712

wav2vec2bert_stats.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c176c2b8850ab2e3ba828bbfa969deaf4566ce55db5f2687b8430b87526ad2
+size 9343