Skip to content

Sort leaderboard by SeedTTS score #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
WWWWxp merged 1 commit into from
Aug 9, 2026
Merged

Sort leaderboard by SeedTTS score #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,22 +12,22 @@ rate of the encoder.

| VAE | Frame rate (Hz) | Latent dim | SeedTTS-Eval | LibriSpeech-PC |
| --- | ---: | ---: | ---: | ---: |
| [DAC](https://github.com/facebookresearch/dacvae/tree/main/dacvae) | 25 | 128 | 0.9569 | 1.0049 |
| [LongCat Wav-VAE](https://github.com/meituan-longcat/LongCat-AudioDiT) | 12 | 64 | 0.8613 | 1.0146 |
| [MingTok-Audio](https://github.com/inclusionAI/Ming-UniAudio) | 50 | 64 | 0.5758 | 0.5641 |
| [Semantic-VAE (1000k)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 64 | 0.2231 | 0.1911 |
| [Semantic-VAE (600k)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 64 | 0.2247 | 0.1926 |
| [Semantic-VAE (dim 16)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 16 | **0.2025** | **0.1778** |
| [Semantic-VAE (dim 64)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 64 | 0.6803 | 0.7222 |
| [Stable Audio Open VAE](https://github.com/Stability-AI/stable-audio-tools) | 21 | 64 | 0.7796 | 0.9137 |
| [VoxCPM AudioVAE](https://github.com/OpenBMB/VoxCPM) | 25 | 64 | 0.7023 | 0.9020 |
| [KVAE-Audio](https://github.com/kandinskylab/kvae-audio) | 50 | 64 | 0.2066 | 0.2428 |
| [Semantic-VAE (1000k)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 64 | 0.2231 | 0.1911 |
| [Semantic-VAE (600k)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 64 | 0.2247 | 0.1926 |
| [MMAudio-16k](https://github.com/hkchengrex/MMAudio) | 31.25 | 20 | 0.4800 | 0.5842 |
| [LTX-2 Audio](https://github.com/Lightricks/LTX-2) | 25 | 128 | 0.4835 | 0.4644 |
| [Ming-Omni 12.5Hz](https://github.com/inclusionAI/Ming-omni-tts) | 12.5 | 64 | 0.4912 | 0.8372 |
| [MingTok-Audio](https://github.com/inclusionAI/Ming-UniAudio) | 50 | 64 | 0.5758 | 0.5641 |
| [Semantic-VAE (dim 64)](https://github.com/ZhikangNiu/Semantic-VAE) | 40 | 64 | 0.6803 | 0.7222 |
| [VoxCPM AudioVAE](https://github.com/OpenBMB/VoxCPM) | 25 | 64 | 0.7023 | 0.9020 |
| [AudioLDM2](https://github.com/haoheliu/AudioLDM2) | 25 | 128 | 0.7103 | 0.8175 |
| [Stable Audio Open VAE](https://github.com/Stability-AI/stable-audio-tools) | 21 | 64 | 0.7796 | 0.9137 |
| [OmniVAE](https://github.com/OpenMOSS/OmniVAE) | 50 | 128 | 0.7902 | 0.7891 |
| [LongCat Wav-VAE](https://github.com/meituan-longcat/LongCat-AudioDiT) | 12 | 64 | 0.8613 | 1.0146 |
| [HunyuanVideo-Foley](https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley) | 50 | 128 | 0.9315 | 0.9386 |
| [DAC](https://github.com/facebookresearch/dacvae/tree/main/dacvae) | 25 | 128 | 0.9569 | 1.0049 |
| [SAME-L](https://github.com/Stability-AI/stable-audio-3) | 10.77 | 256 | 1.0894 | 1.2404 |
| [SAME-S](https://github.com/Stability-AI/stable-audio-3) | 10.77 | 256 | 1.5220 | 1.7352 |
| [AudioLDM](https://github.com/haoheliu/AudioLDM) | 25 | 128 | 1.8676 | 2.2150 |
Expand Down
16 changes: 8 additions & 8 deletions leaderboard.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,20 +1,20 @@
model_id,model,reference_url,frame_rate_hz,latent_dim,seedtts_eval_items,seedtts_eval_slip,librispeech_pc_items,librispeech_pc_slip
dac,DAC,https://github.com/facebookresearch/dacvae/tree/main/dacvae,25,128,3108,0.9568709904537772,1127,1.0049496753892913
longcat_vae,LongCat Wav-VAE,https://github.com/meituan-longcat/LongCat-AudioDiT,12,64,3108,0.8613102635488661,1127,1.0145516145772573
mingtok,MingTok-Audio,https://github.com/inclusionAI/Ming-UniAudio,50,64,3108,0.575821561049603,1127,0.5641497170297263
semantic_vae,Semantic-VAE (1000k),https://github.com/ZhikangNiu/Semantic-VAE,40,64,3108,0.2231031494615381,1127,0.19108301530087118
semantic_vae_600k,Semantic-VAE (600k),https://github.com/ZhikangNiu/Semantic-VAE,40,64,3108,0.22469498194018672,1127,0.1926484303807255
semantic_vae_acoustic_dim16,Semantic-VAE (dim 16),https://github.com/ZhikangNiu/Semantic-VAE,40,16,3108,0.20249130695334738,1127,0.17778720933451264
semantic_vae_acoustic_dim64,Semantic-VAE (dim 64),https://github.com/ZhikangNiu/Semantic-VAE,40,64,3108,0.6803207543198304,1127,0.7221938199771134
stable_audio_open_1_0_vae,Stable Audio Open VAE,https://github.com/Stability-AI/stable-audio-tools,21,64,3108,0.7795683069139887,1127,0.9136771764114867
voxcpm_vae,VoxCPM AudioVAE,https://github.com/OpenBMB/VoxCPM,25,64,3108,0.7022813864479693,1127,0.9020354659108978
kvae_audio,KVAE-Audio,https://github.com/kandinskylab/kvae-audio,50,64,3108,0.2065557541379101,1127,0.24280895985985393
semantic_vae,Semantic-VAE (1000k),https://github.com/ZhikangNiu/Semantic-VAE,40,64,3108,0.2231031494615381,1127,0.19108301530087118
semantic_vae_600k,Semantic-VAE (600k),https://github.com/ZhikangNiu/Semantic-VAE,40,64,3108,0.22469498194018672,1127,0.1926484303807255
mmaudio_16k,MMAudio-16k,https://github.com/hkchengrex/MMAudio,31.25,20,3108,0.4799609285310823,1127,0.5841837898365188
ltx2_audio,LTX-2 Audio,https://github.com/Lightricks/LTX-2,25,128,3108,0.48350454494372774,1127,0.4643737239100124
ming_omni_12hz,Ming-Omni 12.5Hz,https://github.com/inclusionAI/Ming-omni-tts,12.5,64,3108,0.49121076009867093,1127,0.8372175056454173
mingtok,MingTok-Audio,https://github.com/inclusionAI/Ming-UniAudio,50,64,3108,0.575821561049603,1127,0.5641497170297263
semantic_vae_acoustic_dim64,Semantic-VAE (dim 64),https://github.com/ZhikangNiu/Semantic-VAE,40,64,3108,0.6803207543198304,1127,0.7221938199771134
voxcpm_vae,VoxCPM AudioVAE,https://github.com/OpenBMB/VoxCPM,25,64,3108,0.7022813864479693,1127,0.9020354659108978
audioldm2,AudioLDM2,https://github.com/haoheliu/AudioLDM2,25,128,3108,0.7103382312339094,1127,0.817471916579613
stable_audio_open_1_0_vae,Stable Audio Open VAE,https://github.com/Stability-AI/stable-audio-tools,21,64,3108,0.7795683069139887,1127,0.9136771764114867
omnivae_recon,OmniVAE,https://github.com/OpenMOSS/OmniVAE,50,128,3108,0.7902483873843684,1127,0.7891350868151079
longcat_vae,LongCat Wav-VAE,https://github.com/meituan-longcat/LongCat-AudioDiT,12,64,3108,0.8613102635488661,1127,1.0145516145772573
hunyuan_foley,HunyuanVideo-Foley,https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley,50,128,3108,0.9315330892975664,1127,0.938624833216941
dac,DAC,https://github.com/facebookresearch/dacvae/tree/main/dacvae,25,128,3108,0.9568709904537772,1127,1.0049496753892913
same_l,SAME-L,https://github.com/Stability-AI/stable-audio-3,10.7666015625,256,3108,1.0893567469513579,1127,1.2403675374429723
same_s,SAME-S,https://github.com/Stability-AI/stable-audio-3,10.7666015625,256,3108,1.521965857776956,1127,1.7351715787415203
audioldm,AudioLDM,https://github.com/haoheliu/AudioLDM,25,128,3108,1.8676414651258604,1127,2.2149813017532676
Loading