update website

Stability-AI · Dec 1, 2024 · 0e45506 · 0e45506
1 parent d8846aa
commit 0e45506
Show file tree

Hide file tree

Showing 498 changed files with 1,627 additions and 21 deletions.
diff --git a/README.md b/README.md
@@ -1,20 +1 @@
-⚠️ *Warning: This website may not function properly on Safari. For the best experience, please use Google Chrome.*
-
-[`arXiv`](https://arxiv.org/abs/2407.14358): Stable Audio Open paper
-
-[`HuggingFace`](https://huggingface.co/stabilityai/stable-audio-open-1.0): model weights
-
-[`stable-audio-tools`](https://github.com/Stability-AI/stable-audio-tools): code to reproduce Stable Audio
-
-[`stable-audio-metrics`](https://github.com/Stability-AI/stable-audio-metrics): code to evaluate Stable Audio
-
-Stable Audio Open generates variable-length (up to 47s) stereo audio at 44.1kHz from text prompts. It comprises three components: an autoencoder that compresses waveforms into a manageable sequence length, a T5-based text embedding for text conditioning, and a transformer-based diffusion (DiT) model that operates in the latent space of the autoencoder.
-
-## Autoencoder reconstructions
-
-This comparison is useful to evaluate the audio fidelity capabilities of the autoencoder. On the left, we have the ground truth recording. On the right, we take the ground truth recording and end pass it through the any of those autoencoders or neural audio codecs. 
-
-| Ground truth | Stable Audio Open | Stable Audio 2.0 | DAC | 
-| ------------ | ----------------- | ---------------- | --- |
-| <audio controls preload=False><source src="audio/3112.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> | <audio controls preload=False><source src="audio/3112_sdd_sao.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> | <audio controls preload=False><source src="audio/3112_sdd_sa2.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> | <audio controls preload=False><source src="audio/3112_sdd_dac.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> |
-| <audio controls preload=False><source src="audio/4883.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> | <audio controls preload=False><source src="audio/4883_sdd_sao.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> | <audio controls preload=False><source src="audio/4883_sdd_sa2.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> | <audio controls preload=False><source src="audio/4883_sdd_dac.mp3" type="audio/mpeg">Audio not supported by your browser.</audio> |
+# taae_anonymised
diff --git a/arch.png b/arch.png
diff --git a/audio/3112.mp3 b/audio/3112.mp3
diff --git a/audio/3112_sdd_dac.mp3 b/audio/3112_sdd_dac.mp3
diff --git a/audio/3112_sdd_sa2.mp3 b/audio/3112_sdd_sa2.mp3
diff --git a/audio/3112_sdd_sao.mp3 b/audio/3112_sdd_sao.mp3
diff --git a/audio/4883.mp3 b/audio/4883.mp3
diff --git a/audio/4883_sdd_dac.mp3 b/audio/4883_sdd_dac.mp3
diff --git a/audio/4883_sdd_sa2.mp3 b/audio/4883_sdd_sa2.mp3
diff --git a/audio/4883_sdd_sao.mp3 b/audio/4883_sdd_sao.mp3
diff --git a/audios/groundtruth_speech/1089-134691-0001.wav b/audios/groundtruth_speech/1089-134691-0001.wav
diff --git a/audios/groundtruth_speech/121-121726-0010.wav b/audios/groundtruth_speech/121-121726-0010.wav
diff --git a/audios/groundtruth_speech/1284-1180-0010.wav b/audios/groundtruth_speech/1284-1180-0010.wav
diff --git a/audios/groundtruth_speech/1320-122612-0008.wav b/audios/groundtruth_speech/1320-122612-0008.wav
diff --git a/audios/groundtruth_speech/1580-141083-0033.wav b/audios/groundtruth_speech/1580-141083-0033.wav
diff --git a/audios/groundtruth_speech/1995-1837-0024.wav b/audios/groundtruth_speech/1995-1837-0024.wav
diff --git a/audios/groundtruth_speech/2300-131720-0008.wav b/audios/groundtruth_speech/2300-131720-0008.wav
diff --git a/audios/groundtruth_speech/237-134500-0022.wav b/audios/groundtruth_speech/237-134500-0022.wav
diff --git a/audios/groundtruth_speech/260-123286-0018.wav b/audios/groundtruth_speech/260-123286-0018.wav
diff --git a/audios/groundtruth_speech/2830-3980-0050.flac b/audios/groundtruth_speech/2830-3980-0050.flac
diff --git a/audios/groundtruth_speech/3570-5694-0004.wav b/audios/groundtruth_speech/3570-5694-0004.wav
diff --git a/audios/groundtruth_speech/3570-5694-0008.flac b/audios/groundtruth_speech/3570-5694-0008.flac
diff --git a/audios/groundtruth_speech/3570-5695-0003.wav b/audios/groundtruth_speech/3570-5695-0003.wav
diff --git a/audios/groundtruth_speech/3575-170457-0013.wav b/audios/groundtruth_speech/3575-170457-0013.wav
diff --git a/audios/groundtruth_speech/4077-13754-0003.wav b/audios/groundtruth_speech/4077-13754-0003.wav
diff --git a/audios/groundtruth_speech/4446-2271-0001.wav b/audios/groundtruth_speech/4446-2271-0001.wav
diff --git a/audios/groundtruth_speech/4446-2273-0035.wav b/audios/groundtruth_speech/4446-2273-0035.wav
diff --git a/audios/groundtruth_speech/4970-29093-0019.wav b/audios/groundtruth_speech/4970-29093-0019.wav
diff --git a/audios/groundtruth_speech/5683-32865-0013.wav b/audios/groundtruth_speech/5683-32865-0013.wav
diff --git a/audios/groundtruth_speech/5683-32879-0005.wav b/audios/groundtruth_speech/5683-32879-0005.wav
diff --git a/audios/groundtruth_speech/61-70970-0024.flac b/audios/groundtruth_speech/61-70970-0024.flac
diff --git a/audios/groundtruth_speech/6829-68769-0025.wav b/audios/groundtruth_speech/6829-68769-0025.wav
diff --git a/audios/groundtruth_speech/7021-79730-0005.wav b/audios/groundtruth_speech/7021-79730-0005.wav
diff --git a/audios/groundtruth_speech/7729-102255-0023.wav b/audios/groundtruth_speech/7729-102255-0023.wav
diff --git a/audios/groundtruth_speech/8224-274384-0007.wav b/audios/groundtruth_speech/8224-274384-0007.wav
diff --git a/audios/groundtruth_speech/8463-294828-0031.flac b/audios/groundtruth_speech/8463-294828-0031.flac
diff --git a/audios/groundtruth_speech/8555-284447-0007.wav b/audios/groundtruth_speech/8555-284447-0007.wav
diff --git a/audios/groundtruth_speech/8555-292519-0008.wav b/audios/groundtruth_speech/8555-292519-0008.wav
diff --git a/audios/groundtruth_speech/908-31957-0013.wav b/audios/groundtruth_speech/908-31957-0013.wav
diff --git a/audios/groundtruth_speech/908-31957-0024.flac b/audios/groundtruth_speech/908-31957-0024.flac
diff --git a/audios/groundtruth_speech_mls/2037_2597_000256.wav b/audios/groundtruth_speech_mls/2037_2597_000256.wav
diff --git a/audios/groundtruth_speech_mls/mls_french/123_394_000304.wav b/audios/groundtruth_speech_mls/mls_french/123_394_000304.wav
diff --git a/audios/groundtruth_speech_mls/mls_french/9804_10527_000675.wav b/audios/groundtruth_speech_mls/mls_french/9804_10527_000675.wav
diff --git a/audios/groundtruth_speech_mls/mls_german/136_82_000142.wav b/audios/groundtruth_speech_mls/mls_german/136_82_000142.wav
diff --git a/audios/groundtruth_speech_mls/mls_german/143_82_000005.wav b/audios/groundtruth_speech_mls/mls_german/143_82_000005.wav
diff --git a/audios/groundtruth_speech_mls/mls_german/2037_2597_000256.wav b/audios/groundtruth_speech_mls/mls_german/2037_2597_000256.wav
diff --git a/audios/groundtruth_speech_mls/mls_german/3503_3039_000356.wav b/audios/groundtruth_speech_mls/mls_german/3503_3039_000356.wav
diff --git a/audios/groundtruth_speech_mls/mls_german/9639_9388_000022.wav b/audios/groundtruth_speech_mls/mls_german/9639_9388_000022.wav
diff --git a/audios/groundtruth_speech_mls/mls_polish/6439_5541_000240.wav b/audios/groundtruth_speech_mls/mls_polish/6439_5541_000240.wav
diff --git a/audios/groundtruth_speech_mls/mls_polish/6892_6779_000015.wav b/audios/groundtruth_speech_mls/mls_polish/6892_6779_000015.wav
diff --git a/audios/hubert_hifigan_speech/1320-122612-0008.flac b/audios/hubert_hifigan_speech/1320-122612-0008.flac
diff --git a/audios/hubert_hifigan_speech/1995-1837-0024.flac b/audios/hubert_hifigan_speech/1995-1837-0024.flac
diff --git a/audios/hubert_hifigan_speech/260-123286-0018.flac b/audios/hubert_hifigan_speech/260-123286-0018.flac
diff --git a/audios/hubert_hifigan_speech/4077-13754-0003.flac b/audios/hubert_hifigan_speech/4077-13754-0003.flac
diff --git a/audios/hubert_hifigan_speech/4446-2273-0035.flac b/audios/hubert_hifigan_speech/4446-2273-0035.flac
diff --git a/audios/hubert_hifigan_speech/4970-29093-0019.flac b/audios/hubert_hifigan_speech/4970-29093-0019.flac
diff --git a/audios/hubert_hifigan_speech/5683-32865-0013.flac b/audios/hubert_hifigan_speech/5683-32865-0013.flac
diff --git a/audios/hubert_hifigan_speech/7021-79730-0005.flac b/audios/hubert_hifigan_speech/7021-79730-0005.flac
diff --git a/audios/mimi_4_speech/1089-134691-0001.wav b/audios/mimi_4_speech/1089-134691-0001.wav
diff --git a/audios/mimi_4_speech/121-121726-0010.wav b/audios/mimi_4_speech/121-121726-0010.wav
diff --git a/audios/mimi_4_speech/1284-1180-0010.wav b/audios/mimi_4_speech/1284-1180-0010.wav
diff --git a/audios/mimi_4_speech/1320-122612-0008.wav b/audios/mimi_4_speech/1320-122612-0008.wav
diff --git a/audios/mimi_4_speech/1580-141083-0033.wav b/audios/mimi_4_speech/1580-141083-0033.wav
diff --git a/audios/mimi_4_speech/1995-1837-0024.wav b/audios/mimi_4_speech/1995-1837-0024.wav
diff --git a/audios/mimi_4_speech/2300-131720-0008.wav b/audios/mimi_4_speech/2300-131720-0008.wav
diff --git a/audios/mimi_4_speech/237-134500-0022.wav b/audios/mimi_4_speech/237-134500-0022.wav
diff --git a/audios/mimi_4_speech/260-123286-0018.wav b/audios/mimi_4_speech/260-123286-0018.wav
diff --git a/audios/mimi_4_speech/3570-5694-0004.wav b/audios/mimi_4_speech/3570-5694-0004.wav
diff --git a/audios/mimi_4_speech/3570-5695-0003.wav b/audios/mimi_4_speech/3570-5695-0003.wav
diff --git a/audios/mimi_4_speech/3575-170457-0013.wav b/audios/mimi_4_speech/3575-170457-0013.wav
diff --git a/audios/mimi_4_speech/4077-13754-0003.wav b/audios/mimi_4_speech/4077-13754-0003.wav
diff --git a/audios/mimi_4_speech/4446-2271-0001.wav b/audios/mimi_4_speech/4446-2271-0001.wav
diff --git a/audios/mimi_4_speech/4446-2273-0035.wav b/audios/mimi_4_speech/4446-2273-0035.wav
diff --git a/audios/mimi_4_speech/4970-29093-0019.wav b/audios/mimi_4_speech/4970-29093-0019.wav
diff --git a/audios/mimi_4_speech/5683-32865-0013.wav b/audios/mimi_4_speech/5683-32865-0013.wav
diff --git a/audios/mimi_4_speech/5683-32879-0005.wav b/audios/mimi_4_speech/5683-32879-0005.wav
diff --git a/audios/mimi_4_speech/6829-68769-0025.wav b/audios/mimi_4_speech/6829-68769-0025.wav
diff --git a/audios/mimi_4_speech/7021-79730-0005.wav b/audios/mimi_4_speech/7021-79730-0005.wav
diff --git a/audios/mimi_4_speech/7729-102255-0023.wav b/audios/mimi_4_speech/7729-102255-0023.wav
diff --git a/audios/mimi_4_speech/8224-274384-0007.wav b/audios/mimi_4_speech/8224-274384-0007.wav
diff --git a/audios/mimi_4_speech/8555-284447-0007.wav b/audios/mimi_4_speech/8555-284447-0007.wav
diff --git a/audios/mimi_4_speech/8555-292519-0008.wav b/audios/mimi_4_speech/8555-292519-0008.wav
diff --git a/audios/mimi_4_speech/908-31957-0013.wav b/audios/mimi_4_speech/908-31957-0013.wav
diff --git a/audios/mimi_8_speech/1089-134691-0001.wav b/audios/mimi_8_speech/1089-134691-0001.wav
diff --git a/audios/mimi_8_speech/121-121726-0010.wav b/audios/mimi_8_speech/121-121726-0010.wav
diff --git a/audios/mimi_8_speech/1284-1180-0010.wav b/audios/mimi_8_speech/1284-1180-0010.wav
diff --git a/audios/mimi_8_speech/1320-122612-0008.wav b/audios/mimi_8_speech/1320-122612-0008.wav
diff --git a/audios/mimi_8_speech/1580-141083-0033.wav b/audios/mimi_8_speech/1580-141083-0033.wav
diff --git a/audios/mimi_8_speech/1995-1837-0024.wav b/audios/mimi_8_speech/1995-1837-0024.wav
diff --git a/audios/mimi_8_speech/2300-131720-0008.wav b/audios/mimi_8_speech/2300-131720-0008.wav
diff --git a/audios/mimi_8_speech/237-134500-0022.wav b/audios/mimi_8_speech/237-134500-0022.wav
diff --git a/audios/mimi_8_speech/260-123286-0018.wav b/audios/mimi_8_speech/260-123286-0018.wav
diff --git a/audios/mimi_8_speech/3570-5694-0004.wav b/audios/mimi_8_speech/3570-5694-0004.wav
diff --git a/audios/mimi_8_speech/3570-5695-0003.wav b/audios/mimi_8_speech/3570-5695-0003.wav
diff --git a/audios/mimi_8_speech/3575-170457-0013.wav b/audios/mimi_8_speech/3575-170457-0013.wav
diff --git a/audios/mimi_8_speech/4077-13754-0003.wav b/audios/mimi_8_speech/4077-13754-0003.wav
diff --git a/audios/mimi_8_speech/4446-2271-0001.wav b/audios/mimi_8_speech/4446-2271-0001.wav
diff --git a/audios/mimi_8_speech/4446-2273-0035.wav b/audios/mimi_8_speech/4446-2273-0035.wav
diff --git a/audios/mimi_8_speech/4970-29093-0019.wav b/audios/mimi_8_speech/4970-29093-0019.wav
diff --git a/audios/mimi_8_speech/5683-32865-0013.wav b/audios/mimi_8_speech/5683-32865-0013.wav
diff --git a/audios/mimi_8_speech/5683-32879-0005.wav b/audios/mimi_8_speech/5683-32879-0005.wav
diff --git a/audios/mimi_8_speech/6829-68769-0025.wav b/audios/mimi_8_speech/6829-68769-0025.wav
diff --git a/audios/mimi_8_speech/7021-79730-0005.wav b/audios/mimi_8_speech/7021-79730-0005.wav
diff --git a/audios/mimi_8_speech/7729-102255-0023.wav b/audios/mimi_8_speech/7729-102255-0023.wav
diff --git a/audios/mimi_8_speech/8224-274384-0007.wav b/audios/mimi_8_speech/8224-274384-0007.wav
diff --git a/audios/mimi_8_speech/8555-284447-0007.wav b/audios/mimi_8_speech/8555-284447-0007.wav
diff --git a/audios/mimi_8_speech/8555-292519-0008.wav b/audios/mimi_8_speech/8555-292519-0008.wav
diff --git a/audios/mimi_8_speech/908-31957-0013.wav b/audios/mimi_8_speech/908-31957-0013.wav
diff --git a/audios/mimi_8_speech_mls/2037_2597_000256.wav b/audios/mimi_8_speech_mls/2037_2597_000256.wav
diff --git a/audios/mimi_8_speech_mls/mls_french/123_394_000304.wav b/audios/mimi_8_speech_mls/mls_french/123_394_000304.wav
diff --git a/audios/mimi_8_speech_mls/mls_french/9804_10527_000675.wav b/audios/mimi_8_speech_mls/mls_french/9804_10527_000675.wav
diff --git a/audios/mimi_8_speech_mls/mls_german/136_82_000142.wav b/audios/mimi_8_speech_mls/mls_german/136_82_000142.wav
diff --git a/audios/mimi_8_speech_mls/mls_german/143_82_000005.wav b/audios/mimi_8_speech_mls/mls_german/143_82_000005.wav
diff --git a/audios/mimi_8_speech_mls/mls_german/2037_2597_000256.wav b/audios/mimi_8_speech_mls/mls_german/2037_2597_000256.wav
diff --git a/audios/mimi_8_speech_mls/mls_german/3503_3039_000356.wav b/audios/mimi_8_speech_mls/mls_german/3503_3039_000356.wav
diff --git a/audios/mimi_8_speech_mls/mls_german/9639_9388_000022.wav b/audios/mimi_8_speech_mls/mls_german/9639_9388_000022.wav
diff --git a/audios/mimi_8_speech_mls/mls_polish/6439_5541_000240.wav b/audios/mimi_8_speech_mls/mls_polish/6439_5541_000240.wav
diff --git a/audios/mimi_8_speech_mls/mls_polish/6892_6779_000015.wav b/audios/mimi_8_speech_mls/mls_polish/6892_6779_000015.wav
diff --git a/audios/semantiCodec_25_speech/1089-134691-0001.wav b/audios/semantiCodec_25_speech/1089-134691-0001.wav
diff --git a/audios/semantiCodec_25_speech/121-121726-0010.wav b/audios/semantiCodec_25_speech/121-121726-0010.wav
diff --git a/audios/semantiCodec_25_speech/1284-1180-0010.wav b/audios/semantiCodec_25_speech/1284-1180-0010.wav
diff --git a/audios/semantiCodec_25_speech/1320-122612-0008.wav b/audios/semantiCodec_25_speech/1320-122612-0008.wav
diff --git a/audios/semantiCodec_25_speech/1580-141083-0033.wav b/audios/semantiCodec_25_speech/1580-141083-0033.wav
diff --git a/audios/semantiCodec_25_speech/1995-1837-0024.wav b/audios/semantiCodec_25_speech/1995-1837-0024.wav
diff --git a/audios/semantiCodec_25_speech/2300-131720-0008.wav b/audios/semantiCodec_25_speech/2300-131720-0008.wav
diff --git a/audios/semantiCodec_25_speech/237-134500-0022.wav b/audios/semantiCodec_25_speech/237-134500-0022.wav
diff --git a/audios/semantiCodec_25_speech/260-123286-0018.wav b/audios/semantiCodec_25_speech/260-123286-0018.wav
diff --git a/audios/semantiCodec_25_speech/3570-5694-0004.wav b/audios/semantiCodec_25_speech/3570-5694-0004.wav
diff --git a/audios/semantiCodec_25_speech/3570-5695-0003.wav b/audios/semantiCodec_25_speech/3570-5695-0003.wav
diff --git a/audios/semantiCodec_25_speech/3575-170457-0013.wav b/audios/semantiCodec_25_speech/3575-170457-0013.wav
diff --git a/audios/semantiCodec_25_speech/4077-13754-0003.wav b/audios/semantiCodec_25_speech/4077-13754-0003.wav
diff --git a/audios/semantiCodec_25_speech/4446-2271-0001.wav b/audios/semantiCodec_25_speech/4446-2271-0001.wav
diff --git a/audios/semantiCodec_25_speech/4446-2273-0035.wav b/audios/semantiCodec_25_speech/4446-2273-0035.wav
diff --git a/audios/semantiCodec_25_speech/4970-29093-0019.wav b/audios/semantiCodec_25_speech/4970-29093-0019.wav
diff --git a/audios/semantiCodec_25_speech/5683-32865-0013.wav b/audios/semantiCodec_25_speech/5683-32865-0013.wav
diff --git a/audios/semantiCodec_25_speech/5683-32879-0005.wav b/audios/semantiCodec_25_speech/5683-32879-0005.wav
diff --git a/audios/semantiCodec_25_speech/6829-68769-0025.wav b/audios/semantiCodec_25_speech/6829-68769-0025.wav
diff --git a/audios/semantiCodec_25_speech/7021-79730-0005.wav b/audios/semantiCodec_25_speech/7021-79730-0005.wav
diff --git a/audios/semantiCodec_25_speech/7729-102255-0023.wav b/audios/semantiCodec_25_speech/7729-102255-0023.wav
diff --git a/audios/semantiCodec_25_speech/8224-274384-0007.wav b/audios/semantiCodec_25_speech/8224-274384-0007.wav
diff --git a/audios/semantiCodec_25_speech/8555-284447-0007.wav b/audios/semantiCodec_25_speech/8555-284447-0007.wav
diff --git a/audios/semantiCodec_25_speech/8555-292519-0008.wav b/audios/semantiCodec_25_speech/8555-292519-0008.wav
diff --git a/audios/semantiCodec_25_speech/908-31957-0013.wav b/audios/semantiCodec_25_speech/908-31957-0013.wav
diff --git a/audios/semantiCodec_50_speech/1089-134691-0001.wav b/audios/semantiCodec_50_speech/1089-134691-0001.wav
diff --git a/audios/semantiCodec_50_speech/121-121726-0010.wav b/audios/semantiCodec_50_speech/121-121726-0010.wav
diff --git a/audios/semantiCodec_50_speech/1284-1180-0010.wav b/audios/semantiCodec_50_speech/1284-1180-0010.wav
diff --git a/audios/semantiCodec_50_speech/1320-122612-0008.wav b/audios/semantiCodec_50_speech/1320-122612-0008.wav
diff --git a/audios/semantiCodec_50_speech/1580-141083-0033.wav b/audios/semantiCodec_50_speech/1580-141083-0033.wav
diff --git a/audios/semantiCodec_50_speech/1995-1837-0024.wav b/audios/semantiCodec_50_speech/1995-1837-0024.wav
diff --git a/audios/semantiCodec_50_speech/2300-131720-0008.wav b/audios/semantiCodec_50_speech/2300-131720-0008.wav
diff --git a/audios/semantiCodec_50_speech/237-134500-0022.wav b/audios/semantiCodec_50_speech/237-134500-0022.wav
diff --git a/audios/semantiCodec_50_speech/260-123286-0018.wav b/audios/semantiCodec_50_speech/260-123286-0018.wav
diff --git a/audios/semantiCodec_50_speech/3570-5694-0004.wav b/audios/semantiCodec_50_speech/3570-5694-0004.wav
diff --git a/audios/semantiCodec_50_speech/3570-5695-0003.wav b/audios/semantiCodec_50_speech/3570-5695-0003.wav
diff --git a/audios/semantiCodec_50_speech/3575-170457-0013.wav b/audios/semantiCodec_50_speech/3575-170457-0013.wav
diff --git a/audios/semantiCodec_50_speech/4077-13754-0003.wav b/audios/semantiCodec_50_speech/4077-13754-0003.wav
diff --git a/audios/semantiCodec_50_speech/4446-2271-0001.wav b/audios/semantiCodec_50_speech/4446-2271-0001.wav
diff --git a/audios/semantiCodec_50_speech/4446-2273-0035.wav b/audios/semantiCodec_50_speech/4446-2273-0035.wav
diff --git a/audios/semantiCodec_50_speech/4970-29093-0019.wav b/audios/semantiCodec_50_speech/4970-29093-0019.wav
diff --git a/audios/semantiCodec_50_speech/5683-32865-0013.wav b/audios/semantiCodec_50_speech/5683-32865-0013.wav
diff --git a/audios/semantiCodec_50_speech/5683-32879-0005.wav b/audios/semantiCodec_50_speech/5683-32879-0005.wav
diff --git a/audios/semantiCodec_50_speech/6829-68769-0025.wav b/audios/semantiCodec_50_speech/6829-68769-0025.wav
diff --git a/audios/semantiCodec_50_speech/7021-79730-0005.wav b/audios/semantiCodec_50_speech/7021-79730-0005.wav
diff --git a/audios/semantiCodec_50_speech/7729-102255-0023.wav b/audios/semantiCodec_50_speech/7729-102255-0023.wav
diff --git a/audios/semantiCodec_50_speech/8224-274384-0007.wav b/audios/semantiCodec_50_speech/8224-274384-0007.wav
diff --git a/audios/semantiCodec_50_speech/8555-284447-0007.wav b/audios/semantiCodec_50_speech/8555-284447-0007.wav
diff --git a/audios/semantiCodec_50_speech/8555-292519-0008.wav b/audios/semantiCodec_50_speech/8555-292519-0008.wav
diff --git a/audios/semantiCodec_50_speech/908-31957-0013.wav b/audios/semantiCodec_50_speech/908-31957-0013.wav
diff --git a/audios/semantiCodec_50_speech_mls/2037_2597_000256.wav b/audios/semantiCodec_50_speech_mls/2037_2597_000256.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_french/123_394_000304.wav b/audios/semantiCodec_50_speech_mls/mls_french/123_394_000304.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_french/9804_10527_000675.wav b/audios/semantiCodec_50_speech_mls/mls_french/9804_10527_000675.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_german/136_82_000142.wav b/audios/semantiCodec_50_speech_mls/mls_german/136_82_000142.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_german/143_82_000005.wav b/audios/semantiCodec_50_speech_mls/mls_german/143_82_000005.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_german/2037_2597_000256.wav b/audios/semantiCodec_50_speech_mls/mls_german/2037_2597_000256.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_german/3503_3039_000356.wav b/audios/semantiCodec_50_speech_mls/mls_german/3503_3039_000356.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_german/9639_9388_000022.wav b/audios/semantiCodec_50_speech_mls/mls_german/9639_9388_000022.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_polish/6439_5541_000240.wav b/audios/semantiCodec_50_speech_mls/mls_polish/6439_5541_000240.wav
diff --git a/audios/semantiCodec_50_speech_mls/mls_polish/6892_6779_000015.wav b/audios/semantiCodec_50_speech_mls/mls_polish/6892_6779_000015.wav
diff --git a/audios/speech_tokenizer_3vq_mls/2037_2597_000256.wav b/audios/speech_tokenizer_3vq_mls/2037_2597_000256.wav
diff --git a/audios/speech_tokenizer_3vq_mls/9639_9388_000022.wav b/audios/speech_tokenizer_3vq_mls/9639_9388_000022.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_french/123_394_000304.wav b/audios/speech_tokenizer_3vq_mls/mls_french/123_394_000304.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_french/9804_10527_000675.wav b/audios/speech_tokenizer_3vq_mls/mls_french/9804_10527_000675.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_german/136_82_000142.wav b/audios/speech_tokenizer_3vq_mls/mls_german/136_82_000142.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_german/143_82_000005.wav b/audios/speech_tokenizer_3vq_mls/mls_german/143_82_000005.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_german/2037_2597_000256.wav b/audios/speech_tokenizer_3vq_mls/mls_german/2037_2597_000256.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_german/3503_3039_000356.wav b/audios/speech_tokenizer_3vq_mls/mls_german/3503_3039_000356.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_german/9639_9388_000022.wav b/audios/speech_tokenizer_3vq_mls/mls_german/9639_9388_000022.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_polish/6439_5541_000240.wav b/audios/speech_tokenizer_3vq_mls/mls_polish/6439_5541_000240.wav
diff --git a/audios/speech_tokenizer_3vq_mls/mls_polish/6892_6779_000015.wav b/audios/speech_tokenizer_3vq_mls/mls_polish/6892_6779_000015.wav
diff --git a/audios/speechgpt_mls/mls_french/123_394_000304.wav b/audios/speechgpt_mls/mls_french/123_394_000304.wav
diff --git a/audios/speechgpt_mls/mls_french/9804_10527_000675.wav b/audios/speechgpt_mls/mls_french/9804_10527_000675.wav
diff --git a/audios/speechgpt_mls/mls_german/136_82_000142.wav b/audios/speechgpt_mls/mls_german/136_82_000142.wav
diff --git a/audios/speechgpt_mls/mls_german/3503_3039_000356.wav b/audios/speechgpt_mls/mls_german/3503_3039_000356.wav
diff --git a/audios/speechgpt_mls/mls_polish/6439_5541_000240.wav b/audios/speechgpt_mls/mls_polish/6439_5541_000240.wav
diff --git a/audios/speechgpt_mls/mls_polish/6892_6779_000015.wav b/audios/speechgpt_mls/mls_polish/6892_6779_000015.wav
diff --git a/audios/tae_causal_highkbps_speech/2830-3980-0050.wav b/audios/tae_causal_highkbps_speech/2830-3980-0050.wav
diff --git a/audios/tae_causal_highkbps_speech/3570-5694-0008.wav b/audios/tae_causal_highkbps_speech/3570-5694-0008.wav
diff --git a/audios/tae_causal_highkbps_speech/61-70970-0024.wav b/audios/tae_causal_highkbps_speech/61-70970-0024.wav
diff --git a/audios/tae_causal_highkbps_speech/8463-294828-0031.wav b/audios/tae_causal_highkbps_speech/8463-294828-0031.wav
diff --git a/audios/tae_causal_highkbps_speech/908-31957-0024.wav b/audios/tae_causal_highkbps_speech/908-31957-0024.wav
diff --git a/audios/tae_highkbps_speech/.DS_Store b/audios/tae_highkbps_speech/.DS_Store
diff --git a/audios/tae_highkbps_speech/121-121726-0010.wav b/audios/tae_highkbps_speech/121-121726-0010.wav
diff --git a/audios/tae_highkbps_speech/1320-122612-0008.wav b/audios/tae_highkbps_speech/1320-122612-0008.wav
diff --git a/audios/tae_highkbps_speech/1995-1837-0024.wav b/audios/tae_highkbps_speech/1995-1837-0024.wav
diff --git a/audios/tae_highkbps_speech/260-123286-0018.wav b/audios/tae_highkbps_speech/260-123286-0018.wav
diff --git a/audios/tae_highkbps_speech/2830-3980-0050.wav b/audios/tae_highkbps_speech/2830-3980-0050.wav
diff --git a/audios/tae_highkbps_speech/3570-5694-0008.wav b/audios/tae_highkbps_speech/3570-5694-0008.wav
diff --git a/audios/tae_highkbps_speech/4077-13754-0003.wav b/audios/tae_highkbps_speech/4077-13754-0003.wav
diff --git a/audios/tae_highkbps_speech/4446-2273-0035.wav b/audios/tae_highkbps_speech/4446-2273-0035.wav
diff --git a/audios/tae_highkbps_speech/4970-29093-0019.wav b/audios/tae_highkbps_speech/4970-29093-0019.wav
diff --git a/audios/tae_highkbps_speech/5683-32865-0013.wav b/audios/tae_highkbps_speech/5683-32865-0013.wav
diff --git a/audios/tae_highkbps_speech/61-70970-0024.wav b/audios/tae_highkbps_speech/61-70970-0024.wav
diff --git a/audios/tae_highkbps_speech/7021-79730-0005.wav b/audios/tae_highkbps_speech/7021-79730-0005.wav
diff --git a/audios/tae_highkbps_speech/8463-294828-0031.wav b/audios/tae_highkbps_speech/8463-294828-0031.wav
diff --git a/audios/tae_highkbps_speech/8555-292519-0008.wav b/audios/tae_highkbps_speech/8555-292519-0008.wav
diff --git a/audios/tae_highkbps_speech/908-31957-0024.wav b/audios/tae_highkbps_speech/908-31957-0024.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_french/123_394_000304.wav b/audios/tae_highkbps_speech_mls/mls_french/123_394_000304.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_french/9804_10527_000675.wav b/audios/tae_highkbps_speech_mls/mls_french/9804_10527_000675.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_german/136_82_000142.wav b/audios/tae_highkbps_speech_mls/mls_german/136_82_000142.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_german/143_82_000005.wav b/audios/tae_highkbps_speech_mls/mls_german/143_82_000005.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_german/2037_2597_000256.wav b/audios/tae_highkbps_speech_mls/mls_german/2037_2597_000256.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_german/3503_3039_000356.wav b/audios/tae_highkbps_speech_mls/mls_german/3503_3039_000356.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_german/9639_9388_000022.wav b/audios/tae_highkbps_speech_mls/mls_german/9639_9388_000022.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_polish/6439_5541_000240.wav b/audios/tae_highkbps_speech_mls/mls_polish/6439_5541_000240.wav
diff --git a/audios/tae_highkbps_speech_mls/mls_polish/6892_6779_000015.wav b/audios/tae_highkbps_speech_mls/mls_polish/6892_6779_000015.wav
diff --git a/audios/tae_lowkbps_speech/1089-134691-0001.wav b/audios/tae_lowkbps_speech/1089-134691-0001.wav
diff --git a/audios/tae_lowkbps_speech/121-121726-0010.wav b/audios/tae_lowkbps_speech/121-121726-0010.wav
diff --git a/audios/tae_lowkbps_speech/1284-1180-0010.wav b/audios/tae_lowkbps_speech/1284-1180-0010.wav
diff --git a/audios/tae_lowkbps_speech/1320-122612-0008.wav b/audios/tae_lowkbps_speech/1320-122612-0008.wav
diff --git a/audios/tae_lowkbps_speech/1580-141083-0033.wav b/audios/tae_lowkbps_speech/1580-141083-0033.wav
diff --git a/audios/tae_lowkbps_speech/1995-1837-0024.wav b/audios/tae_lowkbps_speech/1995-1837-0024.wav
diff --git a/audios/tae_lowkbps_speech/2300-131720-0008.wav b/audios/tae_lowkbps_speech/2300-131720-0008.wav
diff --git a/audios/tae_lowkbps_speech/237-134500-0022.wav b/audios/tae_lowkbps_speech/237-134500-0022.wav
diff --git a/audios/tae_lowkbps_speech/260-123286-0018.wav b/audios/tae_lowkbps_speech/260-123286-0018.wav
diff --git a/audios/tae_lowkbps_speech/3570-5694-0004.wav b/audios/tae_lowkbps_speech/3570-5694-0004.wav
diff --git a/audios/tae_lowkbps_speech/3570-5695-0003.wav b/audios/tae_lowkbps_speech/3570-5695-0003.wav
diff --git a/audios/tae_lowkbps_speech/3575-170457-0013.wav b/audios/tae_lowkbps_speech/3575-170457-0013.wav
diff --git a/audios/tae_lowkbps_speech/4077-13754-0003.wav b/audios/tae_lowkbps_speech/4077-13754-0003.wav
diff --git a/audios/tae_lowkbps_speech/4446-2271-0001.wav b/audios/tae_lowkbps_speech/4446-2271-0001.wav
diff --git a/audios/tae_lowkbps_speech/4446-2273-0035.wav b/audios/tae_lowkbps_speech/4446-2273-0035.wav
diff --git a/audios/tae_lowkbps_speech/4970-29093-0019.wav b/audios/tae_lowkbps_speech/4970-29093-0019.wav
diff --git a/audios/tae_lowkbps_speech/5683-32865-0013.wav b/audios/tae_lowkbps_speech/5683-32865-0013.wav
diff --git a/audios/tae_lowkbps_speech/5683-32879-0005.wav b/audios/tae_lowkbps_speech/5683-32879-0005.wav
diff --git a/audios/tae_lowkbps_speech/6829-68769-0025.wav b/audios/tae_lowkbps_speech/6829-68769-0025.wav
diff --git a/audios/tae_lowkbps_speech/7021-79730-0005.wav b/audios/tae_lowkbps_speech/7021-79730-0005.wav
diff --git a/audios/tae_lowkbps_speech/7729-102255-0023.wav b/audios/tae_lowkbps_speech/7729-102255-0023.wav
diff --git a/audios/tae_lowkbps_speech/8224-274384-0007.wav b/audios/tae_lowkbps_speech/8224-274384-0007.wav
diff --git a/audios/tae_lowkbps_speech/8555-284447-0007.wav b/audios/tae_lowkbps_speech/8555-284447-0007.wav
diff --git a/audios/tae_lowkbps_speech/8555-292519-0008.wav b/audios/tae_lowkbps_speech/8555-292519-0008.wav
diff --git a/audios/tae_lowkbps_speech/908-31957-0013.wav b/audios/tae_lowkbps_speech/908-31957-0013.wav
diff --git a/figs/groundtruth_speech/1089-134691-0001.png b/figs/groundtruth_speech/1089-134691-0001.png
diff --git a/figs/groundtruth_speech/121-121726-0010.png b/figs/groundtruth_speech/121-121726-0010.png
diff --git a/figs/groundtruth_speech/1284-1180-0010.png b/figs/groundtruth_speech/1284-1180-0010.png
diff --git a/figs/groundtruth_speech/1320-122612-0008.png b/figs/groundtruth_speech/1320-122612-0008.png
diff --git a/figs/groundtruth_speech/1580-141083-0033.png b/figs/groundtruth_speech/1580-141083-0033.png
diff --git a/figs/groundtruth_speech/1995-1837-0024.png b/figs/groundtruth_speech/1995-1837-0024.png
diff --git a/figs/groundtruth_speech/2300-131720-0008.png b/figs/groundtruth_speech/2300-131720-0008.png
diff --git a/figs/groundtruth_speech/237-134500-0022.png b/figs/groundtruth_speech/237-134500-0022.png
diff --git a/figs/groundtruth_speech/260-123286-0018.png b/figs/groundtruth_speech/260-123286-0018.png
diff --git a/figs/groundtruth_speech/2830-3980-0050.png b/figs/groundtruth_speech/2830-3980-0050.png
diff --git a/figs/groundtruth_speech/3570-5694-0004.png b/figs/groundtruth_speech/3570-5694-0004.png
diff --git a/figs/groundtruth_speech/3570-5695-0003.png b/figs/groundtruth_speech/3570-5695-0003.png
diff --git a/figs/groundtruth_speech/3575-170457-0013.png b/figs/groundtruth_speech/3575-170457-0013.png
diff --git a/figs/groundtruth_speech/4077-13754-0003.png b/figs/groundtruth_speech/4077-13754-0003.png
diff --git a/figs/groundtruth_speech/4446-2271-0001.png b/figs/groundtruth_speech/4446-2271-0001.png
diff --git a/figs/groundtruth_speech/4446-2273-0035.png b/figs/groundtruth_speech/4446-2273-0035.png
diff --git a/figs/groundtruth_speech/4970-29093-0019.png b/figs/groundtruth_speech/4970-29093-0019.png
diff --git a/figs/groundtruth_speech/5683-32865-0013.png b/figs/groundtruth_speech/5683-32865-0013.png
diff --git a/figs/groundtruth_speech/5683-32879-0005.png b/figs/groundtruth_speech/5683-32879-0005.png
diff --git a/figs/groundtruth_speech/61-70970-0024.png b/figs/groundtruth_speech/61-70970-0024.png
diff --git a/figs/groundtruth_speech/6829-68769-0025.png b/figs/groundtruth_speech/6829-68769-0025.png
diff --git a/figs/groundtruth_speech/7021-79730-0005.png b/figs/groundtruth_speech/7021-79730-0005.png
diff --git a/figs/groundtruth_speech/7729-102255-0023.png b/figs/groundtruth_speech/7729-102255-0023.png
diff --git a/figs/groundtruth_speech/8224-274384-0007.png b/figs/groundtruth_speech/8224-274384-0007.png
diff --git a/figs/groundtruth_speech/8463-294828-0031.png b/figs/groundtruth_speech/8463-294828-0031.png
diff --git a/figs/groundtruth_speech/8555-284447-0007.png b/figs/groundtruth_speech/8555-284447-0007.png
diff --git a/figs/groundtruth_speech/8555-292519-0008.png b/figs/groundtruth_speech/8555-292519-0008.png
diff --git a/figs/groundtruth_speech/908-31957-0013.png b/figs/groundtruth_speech/908-31957-0013.png
diff --git a/figs/groundtruth_speech/908-31957-0024.png b/figs/groundtruth_speech/908-31957-0024.png
diff --git a/figs/groundtruth_speech_mls/mls_french/123_394_000304.png b/figs/groundtruth_speech_mls/mls_french/123_394_000304.png
diff --git a/figs/groundtruth_speech_mls/mls_french/9804_10527_000675.png b/figs/groundtruth_speech_mls/mls_french/9804_10527_000675.png
diff --git a/figs/groundtruth_speech_mls/mls_german/136_82_000142.png b/figs/groundtruth_speech_mls/mls_german/136_82_000142.png
diff --git a/figs/groundtruth_speech_mls/mls_german/143_82_000005.png b/figs/groundtruth_speech_mls/mls_german/143_82_000005.png
diff --git a/figs/groundtruth_speech_mls/mls_german/2037_2597_000256.png b/figs/groundtruth_speech_mls/mls_german/2037_2597_000256.png
diff --git a/figs/groundtruth_speech_mls/mls_german/3503_3039_000356.png b/figs/groundtruth_speech_mls/mls_german/3503_3039_000356.png
diff --git a/figs/groundtruth_speech_mls/mls_german/9639_9388_000022.png b/figs/groundtruth_speech_mls/mls_german/9639_9388_000022.png
diff --git a/figs/groundtruth_speech_mls/mls_polish/6439_5541_000240.png b/figs/groundtruth_speech_mls/mls_polish/6439_5541_000240.png
diff --git a/figs/groundtruth_speech_mls/mls_polish/6892_6779_000015.png b/figs/groundtruth_speech_mls/mls_polish/6892_6779_000015.png
diff --git a/figs/hubert_hifigan_speech/1320-122612-0008.png b/figs/hubert_hifigan_speech/1320-122612-0008.png
diff --git a/figs/hubert_hifigan_speech/1995-1837-0024.png b/figs/hubert_hifigan_speech/1995-1837-0024.png
diff --git a/figs/hubert_hifigan_speech/260-123286-0018.png b/figs/hubert_hifigan_speech/260-123286-0018.png
diff --git a/figs/hubert_hifigan_speech/4077-13754-0003.png b/figs/hubert_hifigan_speech/4077-13754-0003.png
diff --git a/figs/hubert_hifigan_speech/4446-2273-0035.png b/figs/hubert_hifigan_speech/4446-2273-0035.png
diff --git a/figs/hubert_hifigan_speech/4970-29093-0019.png b/figs/hubert_hifigan_speech/4970-29093-0019.png
diff --git a/figs/hubert_hifigan_speech/5683-32865-0013.png b/figs/hubert_hifigan_speech/5683-32865-0013.png
diff --git a/figs/hubert_hifigan_speech/7021-79730-0005.png b/figs/hubert_hifigan_speech/7021-79730-0005.png
diff --git a/figs/mimi_4_speech/1089-134691-0001.png b/figs/mimi_4_speech/1089-134691-0001.png
diff --git a/figs/mimi_4_speech/121-121726-0010.png b/figs/mimi_4_speech/121-121726-0010.png
diff --git a/figs/mimi_4_speech/1284-1180-0010.png b/figs/mimi_4_speech/1284-1180-0010.png
diff --git a/figs/mimi_4_speech/1320-122612-0008.png b/figs/mimi_4_speech/1320-122612-0008.png