diff --git a/Docker/download.py b/Docker/download.py
new file mode 100644
index 0000000..46becac
--- /dev/null
+++ b/Docker/download.py
@@ -0,0 +1,7 @@
+# Download moda ASR related models
+from modelscope import snapshot_download
+model_dir = snapshot_download('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
+model_dir = snapshot_download('damo/speech_fsmn_vad_zh-cn-16k-common-pytorch')
+model_dir = snapshot_download('damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch')
+
+
diff --git a/Dockerfile b/Dockerfile
index cbf92cb..ac85a4b 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -2,7 +2,7 @@
 FROM cnstark/pytorch:2.0.1-py3.9.17-cuda11.8.0-ubuntu20.04
 
 LABEL maintainer="breakstring@hotmail.com"
-LABEL version="dev-20240123.03"
+LABEL version="dev-20240127"
 LABEL description="Docker image for GPT-SoVITS"
 
 
@@ -18,27 +18,19 @@ RUN apt-get update && \
 WORKDIR /workspace
 COPY . /workspace
 
+# install python packages
+RUN pip install -r requirements.txt
+
 # Download models
 RUN chmod +x /workspace/Docker/download.sh && /workspace/Docker/download.sh
 
-# 本应该从 requirements.txt 里面安装package，但是由于funasr和modelscope的问题，暂时先在后面手工安装依赖包吧
-RUN pip install --no-cache-dir torch numpy scipy tensorboard librosa==0.9.2 numba==0.56.4 pytorch-lightning gradio==3.14.0 ffmpeg-python onnxruntime tqdm cn2an pypinyin pyopenjtalk g2p_en chardet transformers jieba psutil PyYAML
-# 这里强制指定了modelscope和funasr的版本，后面damo_asr的模型让它们自己下载
-RUN pip install --no-cache-dir modelscope~=1.10.0 torchaudio sentencepiece funasr~=0.8.7
+# Download moda ASR related
+RUN python /workspace/Docker/download.py
 
-# 先屏蔽掉，让容器里自己下载
-# Clone damo_asr
-#WORKDIR /workspace/tools/damo_asr/models
-#RUN git clone --depth 1 https://www.modelscope.cn/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch && \
-#    (cd speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch && git lfs pull)
-#RUN git clone --depth 1 https://www.modelscope.cn/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch.git speech_fsmn_vad_zh-cn-16k-common-pytorch && \
-#    (cd speech_fsmn_vad_zh-cn-16k-common-pytorch && git lfs pull)
-#RUN git clone --depth 1 https://www.modelscope.cn/iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch.git punc_ct-transformer_zh-cn-common-vocab272727-pytorch && \
-#    (cd punc_ct-transformer_zh-cn-common-vocab272727-pytorch && git lfs pull)
+# Download nltk realted
+RUN python -m nltk.downloader averaged_perceptron_tagger
+RUN python -m nltk.downloader cmudict
 
-#RUN parallel --will-cite -a /workspace/Docker/damo.sha256 "echo -n {} | sha256sum -c"
-
-#WORKDIR /workspace
 
 EXPOSE 9870
 EXPOSE 9871
diff --git a/README.md b/README.md
index 8613816..6d5dd22 100644
--- a/README.md
+++ b/README.md
@@ -121,8 +121,9 @@ For UVR5 (Vocals/Accompaniment Separation & Reverberation Removal, additionally)
 
 ### Using Docker
 
-#### docker-compose.yaml configuration
+#### docker-compose.yaml configuration 
 
+0. Regarding image tags: Due to rapid updates in the codebase and the slow process of packaging and testing images, please check [Docker Hub](https://hub.docker.com/r/breakstring/gpt-sovits) for the currently packaged latest images and select as per your situation, or alternatively, build locally using a Dockerfile according to your own needs.
 1. Environment Variables：
   - is_half: Controls half-precision/double-precision. This is typically the cause if the content under the directories 4-cnhubert/5-wav32k is not generated correctly during the "SSL extracting" step. Adjust to True or False based on your actual situation.
 
@@ -140,7 +141,7 @@ docker compose -f "docker-compose.yaml" up -d
 
 As above, modify the corresponding parameters based on your actual situation, then run the following command:
 ```
-docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-DockerTest\output:/workspace/output --volume=G:\GPT-SoVITS-DockerTest\logs:/workspace/logs --volume=G:\GPT-SoVITS-DockerTest\SoVITS_weights:/workspace/SoVITS_weights --workdir=/workspace -p 9870:9870 -p 9871:9871 -p 9872:9872 -p 9873:9873 -p 9874:9874 --shm-size="16G" -d breakstring/gpt-sovits:dev-20240123.03
+docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-DockerTest\output:/workspace/output --volume=G:\GPT-SoVITS-DockerTest\logs:/workspace/logs --volume=G:\GPT-SoVITS-DockerTest\SoVITS_weights:/workspace/SoVITS_weights --workdir=/workspace -p 9870:9870 -p 9871:9871 -p 9872:9872 -p 9873:9873 -p 9874:9874 --shm-size="16G" -d breakstring/gpt-sovits:xxxxx
 ```
 
 
diff --git a/docker-compose.yaml b/docker-compose.yaml
index ed6f82a..874824e 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   gpt-sovits:
-    image: breakstring/gpt-sovits:dev-20240123.03
+    image: breakstring/gpt-sovits:xxxxx   # please change the image name and tag base your environment
     container_name: gpt-sovits-container
     environment:
       - is_half=False
diff --git a/docs/cn/README.md b/docs/cn/README.md
index 3b07753..d66b2a5 100644
--- a/docs/cn/README.md
+++ b/docs/cn/README.md
@@ -110,7 +110,7 @@ brew install ffmpeg
 ### 在 Docker 中使用
 
 #### docker-compose.yaml 设置
-
+0. image的标签：由于代码库更新很快，镜像的打包和测试又很慢，所以请自行在 [Docker Hub](https://hub.docker.com/r/breakstring/gpt-sovits) 查看当前打包好的最新的镜像并根据自己的情况选用，或者在本地根据您自己的需求通过Dockerfile进行构建。
 1. 环境变量：
   - is_half: 半精度/双精度控制。在进行 "SSL extracting" 步骤时如果无法正确生成 4-cnhubert/5-wav32k 目录下的内容时，一般都是它引起的，可以根据实际情况来调整为True或者False。
 
@@ -129,7 +129,7 @@ docker compose -f "docker-compose.yaml" up -d
 
 同上，根据您自己的实际情况修改对应的参数，然后运行如下命令：
 ```
-docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-DockerTest\output:/workspace/output --volume=G:\GPT-SoVITS-DockerTest\logs:/workspace/logs --volume=G:\GPT-SoVITS-DockerTest\SoVITS_weights:/workspace/SoVITS_weights --workdir=/workspace -p 9870:9870 -p 9871:9871 -p 9872:9872 -p 9873:9873 -p 9874:9874 --shm-size="16G" -d breakstring/gpt-sovits:dev-20240123.03
+docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-DockerTest\output:/workspace/output --volume=G:\GPT-SoVITS-DockerTest\logs:/workspace/logs --volume=G:\GPT-SoVITS-DockerTest\SoVITS_weights:/workspace/SoVITS_weights --workdir=/workspace -p 9870:9870 -p 9871:9871 -p 9872:9872 -p 9873:9873 -p 9874:9874 --shm-size="16G" -d breakstring/gpt-sovits:xxxxx
 ```
 
 
diff --git a/docs/ja/README.md b/docs/ja/README.md
index af5be46..9486752 100644
--- a/docs/ja/README.md
+++ b/docs/ja/README.md
@@ -106,8 +106,9 @@ brew install ffmpeg
 
 ### Dockerの使用
 
-#### docker-compose.yamlの設定
+#### docker-compose.yamlの設定 
 
+0. イメージのタグについて：コードベースの更新が速く、イメージのパッケージングとテストが遅いため、[Docker Hub](https://hub.docker.com/r/breakstring/gpt-sovits) で現在パッケージされている最新のイメージをご覧になり、ご自身の状況に応じて選択するか、またはご自身のニーズに応じてDockerfileを使用してローカルで構築してください。
 1. 環境変数：
     - `is_half`：半精度／倍精度の制御。"SSL抽出"ステップ中に`4-cnhubert/5-wav32k`ディレクトリ内の内容が正しく生成されない場合、通常これが原因です。実際の状況に応じてTrueまたはFalseに調整してください。
 
@@ -124,7 +125,7 @@ docker compose -f "docker-compose.yaml" up -d
 
 上記と同様に、実際の状況に基づいて対応するパラメータを変更し、次のコマンドを実行します：
 ```markdown
-docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-DockerTest\output:/workspace/output --volume=G:\GPT-SoVITS-DockerTest\logs:/workspace/logs --volume=G:\GPT-SoVITS-DockerTest\SoVITS_weights:/workspace/SoVITS_weights --workdir=/workspace -p 9870:9870 -p 9871:9871 -p 9872:9872 -p 9873:9873 -p 9874:9874 --shm-size="16G" -d breakstring/gpt-sovits:dev-20240123.03
+docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-DockerTest\output:/workspace/output --volume=G:\GPT-SoVITS-DockerTest\logs:/workspace/logs --volume=G:\GPT-SoVITS-DockerTest\SoVITS_weights:/workspace/SoVITS_weights --workdir=/workspace -p 9870:9870 -p 9871:9871 -p 9872:9872 -p 9873:9873 -p 9874:9874 --shm-size="16G" -d breakstring/gpt-sovits:xxxxx
 ```