diff --git a/LICENSE b/LICENSE
deleted file mode 100644
index f49a4e16e68b128803cc2dcea614603632b04eac..0000000000000000000000000000000000000000
--- a/LICENSE
+++ /dev/null
@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
\ No newline at end of file
diff --git a/app.py b/app.py
index 36fb47b18be33f8e27f9b8f3fe076c84b4b2c4ff..e2e4ff9a1b33947f232aaf527411843b912aca55 100644
--- a/app.py
+++ b/app.py
@@ -10,8 +10,7 @@ import os
 CONFIG_PATH = Path("configs/unet/second_stage.yaml")
 CHECKPOINT_PATH = Path("checkpoints/latentsync_unet.pt")
 
-# subprocess.run(["huggingface-cli", "download", "Hyathi/LatentSync", "--local-dir", "checkpoints", "--exclude", "*.git*", "README.md"])
-subprocess.run(["huggingface-cli", "download", "Hyathi/LatentSync", "--local-dir", "checkpoints", "--exclude", "*.git*", "README.md", "--token", os.environ["HF_TOKEN"]])
+subprocess.run(["huggingface-cli", "download", "Hyathi/SoundImage-LipSync", "--local-dir", "checkpoints", "--exclude", "*.git*", "README.md", "--token", os.environ["HF_TOKEN"]])
 
 def process_video(
     video_path,
diff --git a/data_processing_pipeline.sh b/data_processing_pipeline.sh
deleted file mode 100644
index 73f551a4f6d73bd11576861fcf9818e010129499..0000000000000000000000000000000000000000
--- a/data_processing_pipeline.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/bash
-
-python -m preprocess.data_processing_pipeline \
-    --total_num_workers 20 \
-    --per_gpu_num_workers 10 \
-    --resolution 256 \
-    --sync_conf_threshold 3 \
-    --temp_dir temp \
-    --input_dir /mnt/bn/maliva-gen-ai-v2/chunyu.li/VoxCeleb2/raw
diff --git a/eval/eval_sync_conf.py b/eval/eval_sync_conf.py
index 741a0c3505c0206fe4e8076c98e5260c36afbf11..a5570328d21321f8b9c5400527c41a9c413b0814 100644
--- a/eval/eval_sync_conf.py
+++ b/eval/eval_sync_conf.py
@@ -18,7 +18,7 @@ import tqdm
 from statistics import fmean
 from eval.syncnet import SyncNetEval
 from eval.syncnet_detect import SyncNetDetector
-from latentsync.utils.util import red_text
+from soundimage.utils.util import red_text
 import torch
 
 
diff --git a/eval/eval_syncnet_acc.py b/eval/eval_syncnet_acc.py
index acde8d804389b70520eb4f3ccb26b860516a2c4c..636e6862324b7600d4dc1fd6337f96f93aec5741 100644
--- a/eval/eval_syncnet_acc.py
+++ b/eval/eval_syncnet_acc.py
@@ -17,8 +17,8 @@ from tqdm.auto import tqdm
 import torch
 import torch.nn as nn
 from einops import rearrange
-from latentsync.models.syncnet import SyncNet
-from latentsync.data.syncnet_dataset import SyncNetDataset
+from soundimage.models.syncnet import SyncNet
+from soundimage.data.syncnet_dataset import SyncNetDataset
 from diffusers import AutoencoderKL
 from omegaconf import OmegaConf
 from accelerate.utils import set_seed
diff --git a/inference.sh b/inference.sh
deleted file mode 100644
index d032fb2243b92b5ac8dce4dcc4679bfb1022f259..0000000000000000000000000000000000000000
--- a/inference.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/bash
-
-python -m scripts.inference \
-    --unet_config_path "configs/unet/second_stage.yaml" \
-    --inference_ckpt_path "checkpoints/latentsync_unet.pt" \
-    --guidance_scale 1.0 \
-    --video_path "assets/demo1_video.mp4" \
-    --audio_path "assets/demo1_audio.wav" \
-    --video_out_path "video_out.mp4"
diff --git a/latentsync/utils/mask.png b/latentsync/utils/mask.png
deleted file mode 100644
index eb8fdd1f4e1c59a55f9b3604a71946b9833f3ca2..0000000000000000000000000000000000000000
Binary files a/latentsync/utils/mask.png and /dev/null differ
diff --git a/preprocess/affine_transform.py b/preprocess/affine_transform.py
index a9e37fbca1469917788cd4ef33b4660fe17acfff..f389a1895a931edb8dd2fe03cf176d50468bf9e2 100644
--- a/preprocess/affine_transform.py
+++ b/preprocess/affine_transform.py
@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from latentsync.utils.util import read_video, write_video
-from latentsync.utils.image_processor import ImageProcessor
+from soundimage.utils.util import read_video, write_video
+from soundimage.utils.image_processor import ImageProcessor
 import torch
 from einops import rearrange
 import os
diff --git a/preprocess/filter_high_resolution.py b/preprocess/filter_high_resolution.py
index 9c8f2b8873ff86ffe9be934a9bc3f9bd5adbc335..5367936c6f774cac9a9d3233b81cb86107566998 100644
--- a/preprocess/filter_high_resolution.py
+++ b/preprocess/filter_high_resolution.py
@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import mediapipe as mp
-from latentsync.utils.util import read_video
+from soundimage.utils.util import read_video
 import os
 import tqdm
 import shutil
diff --git a/preprocess/remove_broken_videos.py b/preprocess/remove_broken_videos.py
index fc58b38e9ea51ac5ac3efde911a8712885fef096..8f469700596e56999138b110264eb2a2789b24b5 100644
--- a/preprocess/remove_broken_videos.py
+++ b/preprocess/remove_broken_videos.py
@@ -16,8 +16,8 @@ import os
 from multiprocessing import Pool
 import tqdm
 
-from latentsync.utils.av_reader import AVReader
-from latentsync.utils.util import gather_video_paths_recursively
+from soundimage.utils.av_reader import AVReader
+from soundimage.utils.util import gather_video_paths_recursively
 
 
 def remove_broken_video(video_path):
diff --git a/preprocess/remove_incorrect_affined.py b/preprocess/remove_incorrect_affined.py
index baf4a85bbf682258f748312da9c109e60d410e53..8188f19a80d220c6f30428c07e7264aabd4add7a 100644
--- a/preprocess/remove_incorrect_affined.py
+++ b/preprocess/remove_incorrect_affined.py
@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import mediapipe as mp
-from latentsync.utils.util import read_video, gather_video_paths_recursively
+from soundimage.utils.util import read_video, gather_video_paths_recursively
 import os
 import tqdm
 from multiprocessing import Pool
diff --git a/scripts/inference.py b/scripts/inference.py
index 5f92690f14110a580cb147949501aa687367c663..76ca42e87562a66155e18a6357385a414f353663 100644
--- a/scripts/inference.py
+++ b/scripts/inference.py
@@ -16,11 +16,11 @@ import argparse
 from omegaconf import OmegaConf
 import torch
 from diffusers import AutoencoderKL, DDIMScheduler
-from latentsync.models.unet import UNet3DConditionModel
-from latentsync.pipelines.lipsync_pipeline import LipsyncPipeline
+from soundimage.models.unet import UNet3DConditionModel
+from soundimage.pipelines.lipsync_pipeline import LipsyncPipeline
 from diffusers.utils.import_utils import is_xformers_available
 from accelerate.utils import set_seed
-from latentsync.whisper.audio2feature import Audio2Feature
+from soundimage.whisper.audio2feature import Audio2Feature
 
 
 def main(config, args):
diff --git a/scripts/train_syncnet.py b/scripts/train_syncnet.py
index 56b983a29764e45469d94dbe0e3c50357252ed9f..604b2b9c060b3d08f1a3031c2f5b274ac5051f53 100644
--- a/scripts/train_syncnet.py
+++ b/scripts/train_syncnet.py
@@ -18,10 +18,10 @@ import logging
 from omegaconf import OmegaConf
 import shutil
 
-from latentsync.data.syncnet_dataset import SyncNetDataset
-from latentsync.models.syncnet import SyncNet
-from latentsync.models.syncnet_wav2lip import SyncNetWav2Lip
-from latentsync.utils.util import gather_loss, plot_loss_chart
+from soundimage.data.syncnet_dataset import SyncNetDataset
+from soundimage.models.syncnet import SyncNet
+from soundimage.models.syncnet_wav2lip import SyncNetWav2Lip
+from soundimage.utils.util import gather_loss, plot_loss_chart
 from accelerate.utils import set_seed
 
 import torch
@@ -31,7 +31,7 @@ from einops import rearrange
 import torch.distributed as dist
 from torch.nn.parallel import DistributedDataParallel as DDP
 from torch.utils.data.distributed import DistributedSampler
-from latentsync.utils.util import init_dist, cosine_loss
+from soundimage.utils.util import init_dist, cosine_loss
 
 logger = get_logger(__name__)
 
diff --git a/scripts/train_unet.py b/scripts/train_unet.py
index ee1a0a620700a0c19cc5bff4aada7f3276c0b5a8..5ed04ffbb9fc155eba6a7e566ea66009bc7d4009 100644
--- a/scripts/train_unet.py
+++ b/scripts/train_unet.py
@@ -36,18 +36,18 @@ from diffusers.optimization import get_scheduler
 from diffusers.utils.import_utils import is_xformers_available
 from accelerate.utils import set_seed
 
-from latentsync.data.unet_dataset import UNetDataset
-from latentsync.models.unet import UNet3DConditionModel
-from latentsync.models.syncnet import SyncNet
-from latentsync.pipelines.lipsync_pipeline import LipsyncPipeline
-from latentsync.utils.util import (
+from soundimage.data.unet_dataset import UNetDataset
+from soundimage.models.unet import UNet3DConditionModel
+from soundimage.models.syncnet import SyncNet
+from soundimage.pipelines.lipsync_pipeline import LipsyncPipeline
+from soundimage.utils.util import (
     init_dist,
     cosine_loss,
     reversed_forward,
 )
-from latentsync.utils.util import plot_loss_chart, gather_loss
-from latentsync.whisper.audio2feature import Audio2Feature
-from latentsync.trepa import TREPALoss
+from soundimage.utils.util import plot_loss_chart, gather_loss
+from soundimage.whisper.audio2feature import Audio2Feature
+from soundimage.trepa import TREPALoss
 from eval.syncnet import SyncNetEval
 from eval.syncnet_detect import SyncNetDetector
 from eval.eval_sync_conf import syncnet_eval
diff --git a/setup_env.sh b/setup_env.sh
deleted file mode 100644
index 487092c2759d2df3edafd4a02acf7bbdd20dd8c3..0000000000000000000000000000000000000000
--- a/setup_env.sh
+++ /dev/null
@@ -1,23 +0,0 @@
-#!/bin/bash
-
-# Create a new conda environment
-conda create -y -n latentsync python=3.10.13
-conda activate latentsync
-
-# Install ffmpeg
-conda install -y -c conda-forge ffmpeg
-
-# Python dependencies
-pip install -r requirements.txt
-
-# OpenCV dependencies
-sudo apt -y install libgl1
-
-# Download all the checkpoints from HuggingFace
-huggingface-cli download Hyathi/LatentSync --local-dir checkpoints --exclude "*.git*" "README.md"
-
-# Soft links for the auxiliary models
-mkdir -p ~/.cache/torch/hub/checkpoints
-ln -s $(pwd)/checkpoints/auxiliary/2DFAN4-cd938726ad.zip ~/.cache/torch/hub/checkpoints/2DFAN4-cd938726ad.zip
-ln -s $(pwd)/checkpoints/auxiliary/s3fd-619a316812.pth ~/.cache/torch/hub/checkpoints/s3fd-619a316812.pth
-ln -s $(pwd)/checkpoints/auxiliary/vgg16-397923af.pth ~/.cache/torch/hub/checkpoints/vgg16-397923af.pth
diff --git a/latentsync/data/syncnet_dataset.py b/soundimage/data/syncnet_dataset.py
similarity index 100%
rename from latentsync/data/syncnet_dataset.py
rename to soundimage/data/syncnet_dataset.py
diff --git a/latentsync/data/unet_dataset.py b/soundimage/data/unet_dataset.py
similarity index 100%
rename from latentsync/data/unet_dataset.py
rename to soundimage/data/unet_dataset.py
diff --git a/latentsync/models/attention.py b/soundimage/models/attention.py
similarity index 100%
rename from latentsync/models/attention.py
rename to soundimage/models/attention.py
diff --git a/latentsync/models/motion_module.py b/soundimage/models/motion_module.py
similarity index 100%
rename from latentsync/models/motion_module.py
rename to soundimage/models/motion_module.py
diff --git a/latentsync/models/resnet.py b/soundimage/models/resnet.py
similarity index 100%
rename from latentsync/models/resnet.py
rename to soundimage/models/resnet.py
diff --git a/latentsync/models/syncnet.py b/soundimage/models/syncnet.py
similarity index 100%
rename from latentsync/models/syncnet.py
rename to soundimage/models/syncnet.py
diff --git a/latentsync/models/syncnet_wav2lip.py b/soundimage/models/syncnet_wav2lip.py
similarity index 100%
rename from latentsync/models/syncnet_wav2lip.py
rename to soundimage/models/syncnet_wav2lip.py
diff --git a/latentsync/models/unet.py b/soundimage/models/unet.py
similarity index 100%
rename from latentsync/models/unet.py
rename to soundimage/models/unet.py
diff --git a/latentsync/models/unet_blocks.py b/soundimage/models/unet_blocks.py
similarity index 100%
rename from latentsync/models/unet_blocks.py
rename to soundimage/models/unet_blocks.py
diff --git a/latentsync/models/utils.py b/soundimage/models/utils.py
similarity index 100%
rename from latentsync/models/utils.py
rename to soundimage/models/utils.py
diff --git a/latentsync/pipelines/lipsync_pipeline.py b/soundimage/pipelines/lipsync_pipeline.py
similarity index 100%
rename from latentsync/pipelines/lipsync_pipeline.py
rename to soundimage/pipelines/lipsync_pipeline.py
diff --git a/latentsync/trepa/__init__.py b/soundimage/trepa/__init__.py
similarity index 100%
rename from latentsync/trepa/__init__.py
rename to soundimage/trepa/__init__.py
diff --git a/latentsync/trepa/third_party/VideoMAEv2/__init__.py b/soundimage/trepa/third_party/VideoMAEv2/__init__.py
similarity index 100%
rename from latentsync/trepa/third_party/VideoMAEv2/__init__.py
rename to soundimage/trepa/third_party/VideoMAEv2/__init__.py
diff --git a/latentsync/trepa/third_party/VideoMAEv2/utils.py b/soundimage/trepa/third_party/VideoMAEv2/utils.py
similarity index 100%
rename from latentsync/trepa/third_party/VideoMAEv2/utils.py
rename to soundimage/trepa/third_party/VideoMAEv2/utils.py
diff --git a/latentsync/trepa/third_party/VideoMAEv2/videomaev2_finetune.py b/soundimage/trepa/third_party/VideoMAEv2/videomaev2_finetune.py
similarity index 100%
rename from latentsync/trepa/third_party/VideoMAEv2/videomaev2_finetune.py
rename to soundimage/trepa/third_party/VideoMAEv2/videomaev2_finetune.py
diff --git a/latentsync/trepa/third_party/VideoMAEv2/videomaev2_pretrain.py b/soundimage/trepa/third_party/VideoMAEv2/videomaev2_pretrain.py
similarity index 100%
rename from latentsync/trepa/third_party/VideoMAEv2/videomaev2_pretrain.py
rename to soundimage/trepa/third_party/VideoMAEv2/videomaev2_pretrain.py
diff --git a/latentsync/trepa/third_party/__init__.py b/soundimage/trepa/third_party/__init__.py
similarity index 100%
rename from latentsync/trepa/third_party/__init__.py
rename to soundimage/trepa/third_party/__init__.py
diff --git a/latentsync/trepa/utils/__init__.py b/soundimage/trepa/utils/__init__.py
similarity index 100%
rename from latentsync/trepa/utils/__init__.py
rename to soundimage/trepa/utils/__init__.py
diff --git a/latentsync/trepa/utils/data_utils.py b/soundimage/trepa/utils/data_utils.py
similarity index 100%
rename from latentsync/trepa/utils/data_utils.py
rename to soundimage/trepa/utils/data_utils.py
diff --git a/latentsync/trepa/utils/metric_utils.py b/soundimage/trepa/utils/metric_utils.py
similarity index 100%
rename from latentsync/trepa/utils/metric_utils.py
rename to soundimage/trepa/utils/metric_utils.py
diff --git a/latentsync/utils/affine_transform.py b/soundimage/utils/affine_transform.py
similarity index 100%
rename from latentsync/utils/affine_transform.py
rename to soundimage/utils/affine_transform.py
diff --git a/latentsync/utils/audio.py b/soundimage/utils/audio.py
similarity index 100%
rename from latentsync/utils/audio.py
rename to soundimage/utils/audio.py
diff --git a/latentsync/utils/av_reader.py b/soundimage/utils/av_reader.py
similarity index 100%
rename from latentsync/utils/av_reader.py
rename to soundimage/utils/av_reader.py
diff --git a/latentsync/utils/image_processor.py b/soundimage/utils/image_processor.py
similarity index 100%
rename from latentsync/utils/image_processor.py
rename to soundimage/utils/image_processor.py
diff --git a/latentsync/utils/util.py b/soundimage/utils/util.py
similarity index 100%
rename from latentsync/utils/util.py
rename to soundimage/utils/util.py
diff --git a/latentsync/whisper/audio2feature.py b/soundimage/whisper/audio2feature.py
similarity index 100%
rename from latentsync/whisper/audio2feature.py
rename to soundimage/whisper/audio2feature.py
diff --git a/latentsync/whisper/whisper/__init__.py b/soundimage/whisper/whisper/__init__.py
similarity index 100%
rename from latentsync/whisper/whisper/__init__.py
rename to soundimage/whisper/whisper/__init__.py
diff --git a/latentsync/whisper/whisper/__main__.py b/soundimage/whisper/whisper/__main__.py
similarity index 100%
rename from latentsync/whisper/whisper/__main__.py
rename to soundimage/whisper/whisper/__main__.py
diff --git a/latentsync/whisper/whisper/assets/gpt2/merges.txt b/soundimage/whisper/whisper/assets/gpt2/merges.txt
similarity index 100%
rename from latentsync/whisper/whisper/assets/gpt2/merges.txt
rename to soundimage/whisper/whisper/assets/gpt2/merges.txt
diff --git a/latentsync/whisper/whisper/assets/gpt2/special_tokens_map.json b/soundimage/whisper/whisper/assets/gpt2/special_tokens_map.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/gpt2/special_tokens_map.json
rename to soundimage/whisper/whisper/assets/gpt2/special_tokens_map.json
diff --git a/latentsync/whisper/whisper/assets/gpt2/tokenizer_config.json b/soundimage/whisper/whisper/assets/gpt2/tokenizer_config.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/gpt2/tokenizer_config.json
rename to soundimage/whisper/whisper/assets/gpt2/tokenizer_config.json
diff --git a/latentsync/whisper/whisper/assets/gpt2/vocab.json b/soundimage/whisper/whisper/assets/gpt2/vocab.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/gpt2/vocab.json
rename to soundimage/whisper/whisper/assets/gpt2/vocab.json
diff --git a/latentsync/whisper/whisper/assets/mel_filters.npz b/soundimage/whisper/whisper/assets/mel_filters.npz
similarity index 100%
rename from latentsync/whisper/whisper/assets/mel_filters.npz
rename to soundimage/whisper/whisper/assets/mel_filters.npz
diff --git a/latentsync/whisper/whisper/assets/multilingual/added_tokens.json b/soundimage/whisper/whisper/assets/multilingual/added_tokens.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/multilingual/added_tokens.json
rename to soundimage/whisper/whisper/assets/multilingual/added_tokens.json
diff --git a/latentsync/whisper/whisper/assets/multilingual/merges.txt b/soundimage/whisper/whisper/assets/multilingual/merges.txt
similarity index 100%
rename from latentsync/whisper/whisper/assets/multilingual/merges.txt
rename to soundimage/whisper/whisper/assets/multilingual/merges.txt
diff --git a/latentsync/whisper/whisper/assets/multilingual/special_tokens_map.json b/soundimage/whisper/whisper/assets/multilingual/special_tokens_map.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/multilingual/special_tokens_map.json
rename to soundimage/whisper/whisper/assets/multilingual/special_tokens_map.json
diff --git a/latentsync/whisper/whisper/assets/multilingual/tokenizer_config.json b/soundimage/whisper/whisper/assets/multilingual/tokenizer_config.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/multilingual/tokenizer_config.json
rename to soundimage/whisper/whisper/assets/multilingual/tokenizer_config.json
diff --git a/latentsync/whisper/whisper/assets/multilingual/vocab.json b/soundimage/whisper/whisper/assets/multilingual/vocab.json
similarity index 100%
rename from latentsync/whisper/whisper/assets/multilingual/vocab.json
rename to soundimage/whisper/whisper/assets/multilingual/vocab.json
diff --git a/latentsync/whisper/whisper/audio.py b/soundimage/whisper/whisper/audio.py
similarity index 100%
rename from latentsync/whisper/whisper/audio.py
rename to soundimage/whisper/whisper/audio.py
diff --git a/latentsync/whisper/whisper/decoding.py b/soundimage/whisper/whisper/decoding.py
similarity index 100%
rename from latentsync/whisper/whisper/decoding.py
rename to soundimage/whisper/whisper/decoding.py
diff --git a/latentsync/whisper/whisper/model.py b/soundimage/whisper/whisper/model.py
similarity index 100%
rename from latentsync/whisper/whisper/model.py
rename to soundimage/whisper/whisper/model.py
diff --git a/latentsync/whisper/whisper/normalizers/__init__.py b/soundimage/whisper/whisper/normalizers/__init__.py
similarity index 100%
rename from latentsync/whisper/whisper/normalizers/__init__.py
rename to soundimage/whisper/whisper/normalizers/__init__.py
diff --git a/latentsync/whisper/whisper/normalizers/basic.py b/soundimage/whisper/whisper/normalizers/basic.py
similarity index 100%
rename from latentsync/whisper/whisper/normalizers/basic.py
rename to soundimage/whisper/whisper/normalizers/basic.py
diff --git a/latentsync/whisper/whisper/normalizers/english.json b/soundimage/whisper/whisper/normalizers/english.json
similarity index 100%
rename from latentsync/whisper/whisper/normalizers/english.json
rename to soundimage/whisper/whisper/normalizers/english.json
diff --git a/latentsync/whisper/whisper/normalizers/english.py b/soundimage/whisper/whisper/normalizers/english.py
similarity index 100%
rename from latentsync/whisper/whisper/normalizers/english.py
rename to soundimage/whisper/whisper/normalizers/english.py
diff --git a/latentsync/whisper/whisper/tokenizer.py b/soundimage/whisper/whisper/tokenizer.py
similarity index 100%
rename from latentsync/whisper/whisper/tokenizer.py
rename to soundimage/whisper/whisper/tokenizer.py
diff --git a/latentsync/whisper/whisper/transcribe.py b/soundimage/whisper/whisper/transcribe.py
similarity index 100%
rename from latentsync/whisper/whisper/transcribe.py
rename to soundimage/whisper/whisper/transcribe.py
diff --git a/latentsync/whisper/whisper/utils.py b/soundimage/whisper/whisper/utils.py
similarity index 100%
rename from latentsync/whisper/whisper/utils.py
rename to soundimage/whisper/whisper/utils.py
diff --git a/tools/count_videos_time.py b/tools/count_videos_time.py
index cb37842d23c13810a8a2905d20672c289b353ffb..6a04f610ec1ef7666383952bc9177a2016d03277 100644
--- a/tools/count_videos_time.py
+++ b/tools/count_videos_time.py
@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import matplotlib.pyplot as plt
-from latentsync.utils.util import count_video_time, gather_video_paths_recursively
+from soundimage.utils.util import count_video_time, gather_video_paths_recursively
 from tqdm import tqdm
 
 
diff --git a/tools/write_fileslist.py b/tools/write_fileslist.py
index 2132a2468a0a0f28cc841a408546547524e99ee1..849a34f74f07892a26e4537288b59dea5bffe81c 100644
--- a/tools/write_fileslist.py
+++ b/tools/write_fileslist.py
@@ -13,7 +13,7 @@
 # limitations under the License.
 
 from tqdm import tqdm
-from latentsync.utils.util import gather_video_paths_recursively
+from soundimage.utils.util import gather_video_paths_recursively
 
 
 def write_fileslist(fileslist_path):
diff --git a/train_syncnet.sh b/train_syncnet.sh
deleted file mode 100644
index 7a99ab06efb7dbcf0ebd8d518fb284799b4d8ee7..0000000000000000000000000000000000000000
--- a/train_syncnet.sh
+++ /dev/null
@@ -1,4 +0,0 @@
-#!/bin/bash
-
-torchrun --nnodes=1 --nproc_per_node=1 --master_port=25678 -m scripts.train_syncnet \
-    --config_path "configs/syncnet/syncnet_16_pixel.yaml"
diff --git a/train_unet.sh b/train_unet.sh
deleted file mode 100644
index 28f63442c599064c5083f38287c6bcdfda660fc2..0000000000000000000000000000000000000000
--- a/train_unet.sh
+++ /dev/null
@@ -1,4 +0,0 @@
-#!/bin/bash
-
-torchrun --nnodes=1 --nproc_per_node=1 --master_port=25678 -m scripts.train_unet \
-    --unet_config_path "configs/unet/first_stage.yaml"