diff --git a/README.md b/README.md index 652cccd..6d4cb6f 100644 --- a/README.md +++ b/README.md @@ -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 | diff --git a/leaderboard.csv b/leaderboard.csv index 28df0fd..64dd4ee 100644 --- a/leaderboard.csv +++ b/leaderboard.csv @@ -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