Upload 21 files

.gitattributes

@@ -33,3 +33,5 @@ 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
+hf_cache/models--funasr--campplus/blobs/3388cf5fd3493c9ac9c69851d8e7a8badcfb4f3dc631020c4961371646d5ada8 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

pinyin.vocab

@@ -0,0 +1,1728 @@
+A1
+A5
+AI1
+AI2
+AI3
+AI4
+AI5
+AN1
+AN2
+AN3
+AN4
+AN5
+ANG1
+ANG2
+ANG4
+ANG5
+AO1
+AO2
+AO3
+AO4
+AO5
+BA1
+BA2
+BA3
+BA4
+BA5
+BAI1
+BAI2
+BAI3
+BAI4
+BAI5
+BAN1
+BAN2
+BAN3
+BAN4
+BAN5
+BANG1
+BANG2
+BANG3
+BANG4
+BANG5
+BAO1
+BAO2
+BAO3
+BAO4
+BAO5
+BEI1
+BEI2
+BEI3
+BEI4
+BEI5
+BEN1
+BEN2
+BEN3
+BEN4
+BEN5
+BENG1
+BENG2
+BENG3
+BENG4
+BENG5
+BI1
+BI2
+BI3
+BI4
+BI5
+BIAN1
+BIAN2
+BIAN3
+BIAN4
+BIAN5
+BIAO1
+BIAO2
+BIAO3
+BIAO4
+BIAO5
+BIE1
+BIE2
+BIE3
+BIE4
+BIE5
+BIN1
+BIN4
+BIN5
+BING1
+BING2
+BING3
+BING4
+BING5
+BO1
+BO2
+BO3
+BO4
+BO5
+BU2
+BU3
+BU4
+BU5
+CA1
+CA3
+CA5
+CAI1
+CAI2
+CAI3
+CAI4
+CAI5
+CAN1
+CAN2
+CAN3
+CAN4
+CAN5
+CANG1
+CANG2
+CANG5
+CAO1
+CAO2
+CAO3
+CAO5
+CE4
+CE5
+CEN1
+CEN2
+CEN5
+CENG1
+CENG2
+CENG4
+CENG5
+CHA1
+CHA2
+CHA3
+CHA4
+CHA5
+CHAI1
+CHAI2
+CHAI5
+CHAN1
+CHAN2
+CHAN3
+CHAN4
+CHAN5
+CHANG1
+CHANG2
+CHANG3
+CHANG4
+CHANG5
+CHAO1
+CHAO2
+CHAO3
+CHAO5
+CHE1
+CHE2
+CHE3
+CHE4
+CHE5
+CHEN1
+CHEN2
+CHEN3
+CHEN4
+CHEN5
+CHENG1
+CHENG2
+CHENG3
+CHENG4
+CHENG5
+CHI1
+CHI2
+CHI3
+CHI4
+CHI5
+CHONG1
+CHONG2
+CHONG3
+CHONG4
+CHONG5
+CHOU1
+CHOU2
+CHOU3
+CHOU4
+CHOU5
+CHU1
+CHU2
+CHU3
+CHU4
+CHU5
+CHUA1
+CHUAI1
+CHUAI2
+CHUAI3
+CHUAI4
+CHUAI5
+CHUAN1
+CHUAN2
+CHUAN3
+CHUAN4
+CHUAN5
+CHUANG1
+CHUANG2
+CHUANG3
+CHUANG4
+CHUANG5
+CHUI1
+CHUI2
+CHUI5
+CHUN1
+CHUN2
+CHUN3
+CHUN5
+CHUO1
+CHUO4
+CHUO5
+CI1
+CI2
+CI3
+CI4
+CI5
+CONG1
+CONG2
+CONG5
+COU4
+COU5
+CU1
+CU2
+CU4
+CU5
+CUAN1
+CUAN2
+CUAN4
+CUAN5
+CUI1
+CUI2
+CUI3
+CUI4
+CUI5
+CUN1
+CUN2
+CUN3
+CUN4
+CUN5
+CUO1
+CUO2
+CUO4
+CUO5
+DA1
+DA2
+DA3
+DA4
+DA5
+DAI1
+DAI2
+DAI3
+DAI4
+DAI5
+DAN1
+DAN2
+DAN3
+DAN4
+DAN5
+DANG1
+DANG2
+DANG3
+DANG4
+DANG5
+DAO1
+DAO2
+DAO3
+DAO4
+DAO5
+DE1
+DE2
+DE5
+DEI2
+DEI3
+DEI5
+DENG1
+DENG2
+DENG3
+DENG4
+DENG5
+DI1
+DI2
+DI3
+DI4
+DI5
+DIA3
+DIAN1
+DIAN2
+DIAN3
+DIAN4
+DIAN5
+DIAO1
+DIAO2
+DIAO3
+DIAO4
+DIAO5
+DIE1
+DIE2
+DIE4
+DIE5
+DING1
+DING2
+DING3
+DING4
+DING5
+DIU1
+DIU5
+DONG1
+DONG2
+DONG3
+DONG4
+DONG5
+DOU1
+DOU2
+DOU3
+DOU4
+DOU5
+DU1
+DU2
+DU3
+DU4
+DU5
+DUAN1
+DUAN2
+DUAN3
+DUAN4
+DUAN5
+DUI1
+DUI4
+DUI5
+DUN1
+DUN2
+DUN3
+DUN4
+DUN5
+DUO1
+DUO2
+DUO3
+DUO4
+DUO5
+E1
+E2
+E3
+E4
+E5
+EI2
+EI5
+EN1
+EN4
+EN5
+ER2
+ER3
+ER4
+ER5
+FA1
+FA2
+FA3
+FA4
+FA5
+FAN1
+FAN2
+FAN3
+FAN4
+FAN5
+FANG1
+FANG2
+FANG3
+FANG4
+FANG5
+FEI1
+FEI2
+FEI3
+FEI4
+FEI5
+FEN1
+FEN2
+FEN3
+FEN4
+FEN5
+FENG1
+FENG2
+FENG3
+FENG4
+FENG5
+FO2
+FOU2
+FOU3
+FOU5
+FU1
+FU2
+FU3
+FU4
+FU5
+GA1
+GA2
+GA3
+GA4
+GA5
+GAI1
+GAI2
+GAI3
+GAI4
+GAI5
+GAN1
+GAN2
+GAN3
+GAN4
+GAN5
+GANG1
+GANG2
+GANG3
+GANG4
+GANG5
+GAO1
+GAO2
+GAO3
+GAO4
+GAO5
+GE1
+GE2
+GE3
+GE4
+GE5
+GEI2
+GEI3
+GEI5
+GEN1
+GEN2
+GEN3
+GEN4
+GEN5
+GENG1
+GENG2
+GENG3
+GENG4
+GENG5
+GONG1
+GONG2
+GONG3
+GONG4
+GONG5
+GOU1
+GOU2
+GOU3
+GOU4
+GOU5
+GU1
+GU2
+GU3
+GU4
+GU5
+GUA1
+GUA2
+GUA3
+GUA4
+GUA5
+GUAI1
+GUAI2
+GUAI3
+GUAI4
+GUAI5
+GUAN1
+GUAN2
+GUAN3
+GUAN4
+GUAN5
+GUANG1
+GUANG2
+GUANG3
+GUANG4
+GUANG5
+GUI1
+GUI2
+GUI3
+GUI4
+GUI5
+GUN2
+GUN3
+GUN4
+GUN5
+GUO1
+GUO2
+GUO3
+GUO4
+GUO5
+HA1
+HA2
+HA3
+HA5
+HAI1
+HAI2
+HAI3
+HAI4
+HAI5
+HAN1
+HAN2
+HAN3
+HAN4
+HAN5
+HANG1
+HANG2
+HANG4
+HANG5
+HAO1
+HAO2
+HAO3
+HAO4
+HAO5
+HE1
+HE2
+HE4
+HE5
+HEI1
+HEI5
+HEN2
+HEN3
+HEN4
+HEN5
+HENG1
+HENG2
+HENG4
+HENG5
+HONG1
+HONG2
+HONG3
+HONG4
+HONG5
+HOU1
+HOU2
+HOU3
+HOU4
+HOU5
+HU1
+HU2
+HU3
+HU4
+HU5
+HUA1
+HUA2
+HUA4
+HUA5
+HUAI2
+HUAI4
+HUAI5
+HUAN1
+HUAN2
+HUAN3
+HUAN4
+HUAN5
+HUANG1
+HUANG2
+HUANG3
+HUANG4
+HUANG5
+HUI1
+HUI2
+HUI3
+HUI4
+HUI5
+HUN1
+HUN2
+HUN4
+HUN5
+HUO1
+HUO2
+HUO3
+HUO4
+HUO5
+JI1
+JI2
+JI3
+JI4
+JI5
+JIA1
+JIA2
+JIA3
+JIA4
+JIA5
+JIAN1
+JIAN2
+JIAN3
+JIAN4
+JIAN5
+JIANG1
+JIANG2
+JIANG3
+JIANG4
+JIANG5
+JIAO1
+JIAO2
+JIAO3
+JIAO4
+JIAO5
+JIE1
+JIE2
+JIE3
+JIE4
+JIE5
+JIN1
+JIN2
+JIN3
+JIN4
+JIN5
+JING1
+JING2
+JING3
+JING4
+JING5
+JIONG2
+JIONG3
+JIONG5
+JIU1
+JIU2
+JIU3
+JIU4
+JIU5
+JV1
+JV2
+JV3
+JV4
+JV5
+JVAN1
+JVAN2
+JVAN3
+JVAN4
+JVAN5
+JVE1
+JVE2
+JVE4
+JVE5
+JVN1
+JVN4
+JVN5
+KA1
+KA2
+KA3
+KA5
+KAI1
+KAI2
+KAI3
+KAI4
+KAI5
+KAN1
+KAN2
+KAN3
+KAN4
+KAN5
+KANG1
+KANG2
+KANG4
+KANG5
+KAO1
+KAO2
+KAO3
+KAO4
+KAO5
+KE1
+KE2
+KE3
+KE4
+KE5
+KEN2
+KEN3
+KEN5
+KENG1
+KENG5
+KONG1
+KONG2
+KONG3
+KONG4
+KONG5
+KOU1
+KOU2
+KOU3
+KOU4
+KOU5
+KU1
+KU2
+KU3
+KU4
+KU5
+KUA1
+KUA2
+KUA3
+KUA4
+KUA5
+KUAI2
+KUAI3
+KUAI4
+KUAI5
+KUAN1
+KUAN2
+KUAN3
+KUAN5
+KUANG1
+KUANG2
+KUANG4
+KUANG5
+KUI1
+KUI2
+KUI3
+KUI4
+KUI5
+KUN1
+KUN2
+KUN3
+KUN4
+KUN5
+KUO4
+KUO5
+LA1
+LA2
+LA3
+LA4
+LA5
+LAI2
+LAI4
+LAI5
+LAN2
+LAN3
+LAN4
+LAN5
+LANG1
+LANG2
+LANG3
+LANG4
+LANG5
+LAO1
+LAO2
+LAO3
+LAO4
+LAO5
+LE1
+LE4
+LE5
+LEI1
+LEI2
+LEI3
+LEI4
+LEI5
+LENG1
+LENG2
+LENG3
+LENG4
+LENG5
+LI1
+LI2
+LI3
+LI4
+LI5
+LIA2
+LIA3
+LIA5
+LIAN2
+LIAN3
+LIAN4
+LIAN5
+LIANG2
+LIANG3
+LIANG4
+LIANG5
+LIAO1
+LIAO2
+LIAO3
+LIAO4
+LIAO5
+LIE1
+LIE2
+LIE3
+LIE4
+LIE5
+LIN1
+LIN2
+LIN3
+LIN4
+LIN5
+LING2
+LING3
+LING4
+LING5
+LIU1
+LIU2
+LIU3
+LIU4
+LIU5
+LONG1
+LONG2
+LONG3
+LONG4
+LONG5
+LOU1
+LOU2
+LOU3
+LOU4
+LOU5
+LU1
+LU2
+LU3
+LU4
+LU5
+LUAN2
+LUAN3
+LUAN4
+LUAN5
+LUN1
+LUN2
+LUN4
+LUN5
+LUO1
+LUO2
+LUO3
+LUO4
+LUO5
+LV2
+LV3
+LV4
+LV5
+LVE3
+LVE4
+LVE5
+MA1
+MA2
+MA3
+MA4
+MA5
+MAI2
+MAI3
+MAI4
+MAI5
+MAN1
+MAN2
+MAN3
+MAN4
+MAN5
+MANG2
+MANG3
+MANG5
+MAO1
+MAO2
+MAO3
+MAO4
+MAO5
+ME5
+MEI2
+MEI3
+MEI4
+MEI5
+MEN1
+MEN2
+MEN4
+MEN5
+MENG1
+MENG2
+MENG3
+MENG4
+MENG5
+MI1
+MI2
+MI3
+MI4
+MI5
+MIAN2
+MIAN3
+MIAN4
+MIAN5
+MIAO1
+MIAO2
+MIAO3
+MIAO4
+MIAO5
+MIE1
+MIE4
+MIE5
+MIN2
+MIN3
+MIN5
+MING2
+MING3
+MING4
+MING5
+MIU4
+MO1
+MO2
+MO3
+MO4
+MO5
+MOU1
+MOU2
+MOU3
+MOU5
+MU2
+MU3
+MU4
+MU5
+NA1
+NA2
+NA3
+NA4
+NA5
+NAI2
+NAI3
+NAI4
+NAI5
+NAN1
+NAN2
+NAN3
+NAN4
+NAN5
+NANG1
+NANG2
+NANG5
+NAO1
+NAO2
+NAO3
+NAO4
+NAO5
+NE2
+NE4
+NE5
+NEI2
+NEI3
+NEI4
+NEN4
+NEN5
+NENG2
+NENG5
+NI1
+NI2
+NI3
+NI4
+NI5
+NIAN1
+NIAN2
+NIAN3
+NIAN4
+NIAN5
+NIANG2
+NIANG4
+NIANG5
+NIAO2
+NIAO3
+NIAO4
+NIAO5
+NIE1
+NIE4
+NIE5
+NIN2
+NING2
+NING3
+NING4
+NING5
+NIU1
+NIU2
+NIU3
+NIU4
+NIU5
+NONG2
+NONG4
+NONG5
+NU2
+NU3
+NU4
+NU5
+NUAN2
+NUAN3
+NUAN5
+NUO2
+NUO4
+NUO5
+NV2
+NV3
+NV5
+NVE4
+NVE5
+O1
+O2
+O5
+OU1
+OU2
+OU3
+OU4
+OU5
+PA1
+PA2
+PA4
+PA5
+PAI1
+PAI2
+PAI3
+PAI4
+PAI5
+PAN1
+PAN2
+PAN4
+PAN5
+PANG1
+PANG2
+PANG4
+PANG5
+PAO1
+PAO2
+PAO3
+PAO4
+PAO5
+PEI1
+PEI2
+PEI4
+PEI5
+PEN1
+PEN2
+PEN4
+PEN5
+PENG1
+PENG2
+PENG3
+PENG4
+PENG5
+PI1
+PI2
+PI3
+PI4
+PI5
+PIAN1
+PIAN2
+PIAN4
+PIAN5
+PIAO1
+PIAO2
+PIAO3
+PIAO4
+PIAO5
+PIE1
+PIE2
+PIE3
+PIE5
+PIN1
+PIN2
+PIN3
+PIN4
+PIN5
+PING1
+PING2
+PING5
+PO1
+PO2
+PO3
+PO4
+PO5
+POU1
+POU5
+PU1
+PU2
+PU3
+PU4
+PU5
+QI1
+QI2
+QI3
+QI4
+QI5
+QIA1
+QIA3
+QIA4
+QIA5
+QIAN1
+QIAN2
+QIAN3
+QIAN4
+QIAN5
+QIANG1
+QIANG2
+QIANG3
+QIANG4
+QIANG5
+QIAO1
+QIAO2
+QIAO3
+QIAO4
+QIAO5
+QIE1
+QIE2
+QIE3
+QIE4
+QIE5
+QIN1
+QIN2
+QIN3
+QIN4
+QIN5
+QING1
+QING2
+QING3
+QING4
+QING5
+QIONG1
+QIONG2
+QIONG5
+QIU1
+QIU2
+QIU3
+QIU5
+QV1
+QV2
+QV3
+QV4
+QV5
+QVAN1
+QVAN2
+QVAN3
+QVAN4
+QVAN5
+QVE1
+QVE2
+QVE4
+QVE5
+QVN1
+QVN2
+QVN5
+RAN2
+RAN3
+RAN5
+RANG1
+RANG2
+RANG3
+RANG4
+RANG5
+RAO2
+RAO3
+RAO4
+RAO5
+RE2
+RE3
+RE4
+RE5
+REN2
+REN3
+REN4
+REN5
+RENG1
+RENG2
+RENG5
+RI4
+RI5
+RONG1
+RONG2
+RONG3
+RONG5
+ROU2
+ROU4
+ROU5
+RU2
+RU3
+RU4
+RU5
+RUA2
+RUAN2
+RUAN3
+RUAN5
+RUI2
+RUI3
+RUI4
+RUI5
+RUN4
+RUN5
+RUO4
+RUO5
+SA1
+SA2
+SA3
+SA4
+SA5
+SAI1
+SAI4
+SAI5
+SAN1
+SAN2
+SAN3
+SAN4
+SAN5
+SANG1
+SANG2
+SANG3
+SANG4
+SANG5
+SAO1
+SAO2
+SAO3
+SAO4
+SAO5
+SE4
+SE5
+SEN1
+SEN5
+SENG1
+SENG5
+SHA1
+SHA2
+SHA3
+SHA4
+SHA5
+SHAI1
+SHAI2
+SHAI3
+SHAI4
+SHAI5
+SHAN1
+SHAN2
+SHAN3
+SHAN4
+SHAN5
+SHANG1
+SHANG2
+SHANG3
+SHANG4
+SHANG5
+SHAO1
+SHAO2
+SHAO3
+SHAO4
+SHAO5
+SHE1
+SHE2
+SHE3
+SHE4
+SHE5
+SHEI2
+SHEN1
+SHEN2
+SHEN3
+SHEN4
+SHEN5
+SHENG1
+SHENG2
+SHENG3
+SHENG4
+SHENG5
+SHI1
+SHI2
+SHI3
+SHI4
+SHI5
+SHOU1
+SHOU2
+SHOU3
+SHOU4
+SHOU5
+SHU1
+SHU2
+SHU3
+SHU4
+SHU5
+SHUA1
+SHUA2
+SHUA3
+SHUA4
+SHUA5
+SHUAI1
+SHUAI2
+SHUAI3
+SHUAI4
+SHUAI5
+SHUAN1
+SHUAN4
+SHUAN5
+SHUANG1
+SHUANG2
+SHUANG3
+SHUANG5
+SHUI2
+SHUI3
+SHUI4
+SHUI5
+SHUN2
+SHUN3
+SHUN4
+SHUN5
+SHUO1
+SHUO4
+SHUO5
+SI1
+SI2
+SI3
+SI4
+SI5
+SONG1
+SONG2
+SONG3
+SONG4
+SONG5
+SOU1
+SOU2
+SOU3
+SOU4
+SOU5
+SU1
+SU2
+SU4
+SU5
+SUAN1
+SUAN4
+SUAN5
+SUI1
+SUI2
+SUI3
+SUI4
+SUI5
+SUN1
+SUN2
+SUN3
+SUN5
+SUO1
+SUO2
+SUO3
+SUO5
+TA1
+TA2
+TA3
+TA4
+TA5
+TAI1
+TAI2
+TAI4
+TAI5
+TAN1
+TAN2
+TAN3
+TAN4
+TAN5
+TANG1
+TANG2
+TANG3
+TANG4
+TANG5
+TAO1
+TAO2
+TAO3
+TAO4
+TAO5
+TE4
+TE5
+TENG2
+TENG5
+TI1
+TI2
+TI3
+TI4
+TI5
+TIAN1
+TIAN2
+TIAN3
+TIAN5
+TIAO1
+TIAO2
+TIAO3
+TIAO4
+TIAO5
+TIE1
+TIE2
+TIE3
+TIE4
+TIE5
+TING1
+TING2
+TING3
+TING5
+TONG1
+TONG2
+TONG3
+TONG4
+TONG5
+TOU1
+TOU2
+TOU4
+TOU5
+TU1
+TU2
+TU3
+TU4
+TU5
+TUAN1
+TUAN2
+TUAN3
+TUAN4
+TUAN5
+TUI1
+TUI2
+TUI3
+TUI4
+TUI5
+TUN1
+TUN2
+TUN4
+TUN5
+TUO1
+TUO2
+TUO3
+TUO4
+TUO5
+WA1
+WA2
+WA3
+WA4
+WA5
+WAI1
+WAI2
+WAI3
+WAI4
+WAN1
+WAN2
+WAN3
+WAN4
+WAN5
+WANG1
+WANG2
+WANG3
+WANG4
+WANG5
+WEI1
+WEI2
+WEI3
+WEI4
+WEI5
+WEN1
+WEN2
+WEN3
+WEN4
+WEN5
+WENG1
+WENG2
+WENG3
+WENG4
+WENG5
+WO1
+WO2
+WO3
+WO4
+WO5
+WU1
+WU2
+WU3
+WU4
+WU5
+XI1
+XI2
+XI3
+XI4
+XI5
+XIA1
+XIA2
+XIA4
+XIA5
+XIAN1
+XIAN2
+XIAN3
+XIAN4
+XIAN5
+XIANG1
+XIANG2
+XIANG3
+XIANG4
+XIANG5
+XIAO1
+XIAO2
+XIAO3
+XIAO4
+XIAO5
+XIE1
+XIE2
+XIE3
+XIE4
+XIE5
+XIN1
+XIN2
+XIN4
+XIN5
+XING1
+XING2
+XING3
+XING4
+XING5
+XIONG1
+XIONG2
+XIONG5
+XIU1
+XIU2
+XIU3
+XIU4
+XIU5
+XV1
+XV2
+XV3
+XV4
+XV5
+XVAN1
+XVAN2
+XVAN3
+XVAN4
+XVAN5
+XVE1
+XVE2
+XVE3
+XVE4
+XVE5
+XVN1
+XVN2
+XVN4
+XVN5
+YA1
+YA2
+YA3
+YA4
+YA5
+YAN1
+YAN2
+YAN3
+YAN4
+YAN5
+YANG1
+YANG2
+YANG3
+YANG4
+YANG5
+YAO1
+YAO2
+YAO3
+YAO4
+YAO5
+YE1
+YE2
+YE3
+YE4
+YE5
+YI1
+YI2
+YI3
+YI4
+YI5
+YIN1
+YIN2
+YIN3
+YIN4
+YIN5
+YING1
+YING2
+YING3
+YING4
+YING5
+YO1
+YO5
+YONG1
+YONG2
+YONG3
+YONG4
+YONG5
+YOU1
+YOU2
+YOU3
+YOU4
+YOU5
+YU1
+YU2
+YU3
+YU4
+YU5
+YUAN1
+YUAN2
+YUAN3
+YUAN4
+YUAN5
+YUE1
+YUE4
+YUE5
+YUN1
+YUN2
+YUN3
+YUN4
+YUN5
+ZA1
+ZA2
+ZA3
+ZA5
+ZAI1
+ZAI2
+ZAI3
+ZAI4
+ZAI5
+ZAN1
+ZAN2
+ZAN3
+ZAN4
+ZAN5
+ZANG1
+ZANG4
+ZANG5
+ZAO1
+ZAO2
+ZAO3
+ZAO4
+ZAO5
+ZE2
+ZE4
+ZE5
+ZEI2
+ZEI5
+ZEN2
+ZEN3
+ZENG1
+ZENG4
+ZENG5
+ZHA1
+ZHA2
+ZHA3
+ZHA4
+ZHA5
+ZHAI1
+ZHAI2
+ZHAI3
+ZHAI4
+ZHAI5
+ZHAN1
+ZHAN2
+ZHAN3
+ZHAN4
+ZHAN5
+ZHANG1
+ZHANG2
+ZHANG3
+ZHANG4
+ZHANG5
+ZHAO1
+ZHAO2
+ZHAO3
+ZHAO4
+ZHAO5
+ZHE1
+ZHE2
+ZHE3
+ZHE4
+ZHE5
+ZHEN1
+ZHEN2
+ZHEN3
+ZHEN4
+ZHEN5
+ZHENG1
+ZHENG2
+ZHENG3
+ZHENG4
+ZHENG5
+ZHI1
+ZHI2
+ZHI3
+ZHI4
+ZHI5
+ZHONG1
+ZHONG2
+ZHONG3
+ZHONG4
+ZHONG5
+ZHOU1
+ZHOU2
+ZHOU3
+ZHOU4
+ZHOU5
+ZHU1
+ZHU2
+ZHU3
+ZHU4
+ZHU5
+ZHUA1
+ZHUA2
+ZHUA3
+ZHUA5
+ZHUAI1
+ZHUAI3
+ZHUAI4
+ZHUAI5
+ZHUAN1
+ZHUAN2
+ZHUAN3
+ZHUAN4
+ZHUAN5
+ZHUANG1
+ZHUANG4
+ZHUANG5
+ZHUI1
+ZHUI4
+ZHUI5
+ZHUN1
+ZHUN2
+ZHUN3
+ZHUN5
+ZHUO1
+ZHUO2
+ZHUO5
+ZI1
+ZI2
+ZI3
+ZI4
+ZI5
+ZONG1
+ZONG2
+ZONG3
+ZONG4
+ZONG5
+ZOU1
+ZOU2
+ZOU3
+ZOU4
+ZOU5
+ZU1
+ZU2
+ZU3
+ZU5
+ZUAN1
+ZUAN2
+ZUAN3
+ZUAN4
+ZUAN5
+ZUI2
+ZUI3
+ZUI4
+ZUI5
+ZUN1
+ZUN5
+ZUO1
+ZUO2
+ZUO3
+ZUO4
+ZUO5

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

wav2vec2bert_stats.pt

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