Releases: AIVTDevPKevin/AI-VTuber-System
v1.5 Hot Fix 2 (All-in-One)
v1.5 Hot Fix 2 熱補丁
Fixed an issue where edge-tts was not working properly
修正 edge-tts 無法正常運作的問題
Updated to edge-tts v7.2.7
更新至 edge-tts v7.2.7
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
There's no need to install CUDA and cuDNN manually.
The Python environment included in the package already comes with the required CUDA environment.
Since the CUDA environment used is version 12.1, please make sure your Nvidia graphics driver version is higher than 530.x.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
不需要自行安裝CUDA與cuDNN
整合包裡的Python環境已經自帶所需的CUDA環境
由於使用的CUDA環境為12.1，所以請仍須確保你的Nvidia顯卡驅動版本大於530.x
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Alternative Download Link (Google Drive) 備用載點 (Google雲端硬碟)
https://drive.google.com/drive/folders/1-aj3RZb9NYOsh3DvDGh6rHzGmW_IV5zd?usp=sharing
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/12wZVLUJw33gpqiWLpvcvhMpGg7vfl8U_it4feTGciLE/edit?usp=sharing
How to Obtain an API Key in Google AI Studio 如何在 Google AI Studio 獲取 API Key
https://drive.google.com/file/d/1WAwvtkWUyqnOu4QH-ZhlbuyONbQE4Ul1/view?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
turbo: https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt
Full Changelog: ver1.4...ver1.5
v1.5 Hot Fix (All-in-One)
v1.5 Hot Fix 熱補丁
Fix the operational failure of edge-tts caused by an expired authentication certificate.
修復 edge-tts 因驗證到期而無法正常運作的問題
Release Notes 發布內容
- Added new LLM models
新增LLM模型
"gemini-2.5-flash"、"gemini-2.5-flash-lite"
Details of the model updates can be found at
具體模型更新內容可以參考:
https://ai.google.dev/gemini-api/docs/models/gemini
-
Updated to Google Gen AI SDK v1.39.1
使用最新版 Google Gen AI SDK v1.39.1 -
Fixed an issue where edge-tts was not working properly
修正 edge-tts 無法正常運作的問題
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
There's no need to install CUDA and cuDNN manually.
The Python environment included in the package already comes with the required CUDA environment.
Since the CUDA environment used is version 12.1, please make sure your Nvidia graphics driver version is higher than 530.x.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
不需要自行安裝CUDA與cuDNN
整合包裡的Python環境已經自帶所需的CUDA環境
由於使用的CUDA環境為12.1，所以請仍須確保你的Nvidia顯卡驅動版本大於530.x
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Alternative Download Link (Google Drive) 備用載點 (Google雲端硬碟)
https://drive.google.com/drive/folders/1mlGIQBRFMVITSR7cXvIz_7Z28fjCRa00?usp=sharing
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/12wZVLUJw33gpqiWLpvcvhMpGg7vfl8U_it4feTGciLE/edit?usp=sharing
How to Obtain an API Key in Google AI Studio 如何在 Google AI Studio 獲取 API Key
https://drive.google.com/file/d/1WAwvtkWUyqnOu4QH-ZhlbuyONbQE4Ul1/view?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
turbo: https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt
Full Changelog: ver1.4...ver1.5
v1.5 (All-in-One)
Release Notes 發布內容
- Added new LLM models
新增LLM模型
"gemini-2.5-flash"、"gemini-2.5-flash-lite"
Details of the model updates can be found at
具體模型更新內容可以參考:
https://ai.google.dev/gemini-api/docs/models/gemini
-
Updated to Google Gen AI SDK v1.39.1
使用最新版 Google Gen AI SDK v1.39.1 -
Fixed an issue where edge-tts was not working properly
修正 edge-tts 無法正常運作的問題
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
There's no need to install CUDA and cuDNN manually.
The Python environment included in the package already comes with the required CUDA version.
Since the CUDA environment used is version 12.1, please make sure your Nvidia graphics driver version is higher than 530.x.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
不需要自行安裝CUDA與cuDNN
整合包裡的Python環境已經自帶所需的CUDA版本
由於使用的CUDA環境為12.1，所以請仍須確保你的Nvidia顯卡驅動版本大於530.x
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Alternative Download Link (Google Drive) 備用載點 (Google雲端硬碟)
https://drive.google.com/drive/folders/12xTTSSw-8o6jLZSofs81t74jr_5dXpM2?usp=sharing
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/12wZVLUJw33gpqiWLpvcvhMpGg7vfl8U_it4feTGciLE/edit?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
turbo: https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt
Full Changelog: ver1.4...ver1.5
v1.4 (All-in-One)
Release Notes 發布內容
- Added new LLM models
新增LLM模型
"gemini-2.5-pro"、"gemini-2.0-flash"、"gemini-2.0-flash-lite"、"gemini-1.5-flash"、"gemini-1.5-flash-8b"、"gpt-4o"、 "gpt-4.5-preview"
Details of the model updates can be found at
具體模型更新內容可以參考:
https://ai.google.dev/gemini-api/docs/models/gemini
https://platform.openai.com/docs/models
-
Removed some outdated models
移除一些過時的模型 -
Updated google-generativeai version to 0.8.1
更新google-generativeai版本至0.8.1 -
Updated the input method for character prompts and system instructions in LLM Gemini, theoretically improving its ability to adhere to character settings and follow instructions
更新LLM Gemini對於人設提示詞與系統指示的輸入方式，理論上遵從人設與指示的能力均有提升 -
Fixed an issue where YouTube chat content capture could not automatically reconnect after disconnection
修正YouTube聊天室內容捕捉斷線後無法自動重連的問題
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
There's no need to install CUDA and cuDNN manually.
The Python environment included in the package already comes with the required CUDA version.
Since the CUDA environment used is version 12.1, please make sure your Nvidia graphics driver version is higher than 530.x.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
不需要自行安裝CUDA與cuDNN
整合包裡的Python環境已經自帶所需的CUDA版本
由於使用的CUDA環境為12.1，所以請仍須確保你的Nvidia顯卡驅動版本大於530.x
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Alternative Download Link (Google Drive) 備用載點 (Google雲端硬碟)
https://drive.google.com/drive/folders/1PiABLsmgQjA_MsVw74TCRAQ0i_lpx9cp?usp=sharing
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/16DU-DJKMaC-15K6iShLd9ioXc8VqjTLqgMPswsjPjF0/edit?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
turbo: https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt
v1.3 (All-in-One)
Release Notes 發布內容
-
Added new LLM models "gpt-4o-mini" and "gpt-4o-mini-2024-07-18"
新增LLM模型"gpt-4o-mini"、"gpt-4o-mini-2024-07-18" -
Updated tiktoken version to 0.7.0
更新tiktoken版本至0.7.0 -
Fixed an issue where the User Name in the Settings would revert to the default value (PKevin) after restarting the program
修正Setting裡User Name在程式重新開啟後會變為預設值(PKevin) -
Fixed an issue where the Mic Hotkey in the Settings would be checked after restarting the program
修正Setting裡Mic Hotkey在程式重新開啟後都會自動勾選的問題
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
Note! The CUDA Toolkit and cuDNN are not included and must be installed independently.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
注意! CUDA Toolkit與cuDNN需自行安裝
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Alternative Download Link (Google Drive) 備用載點 (Google雲端硬碟)
https://drive.google.com/drive/folders/1FK5Ko0GV_p7LqsyT3Hnw3HCmzqIBH_-_?usp=sharing
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/1vfRmPHt-LS9Fw5xn6GYXMA2tdae0seam6GvYOYrIXNY/edit?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx?lang=tw
CUDA Toolkit
https://developer.nvidia.com/cuda-12-1-1-download-archive
cuDNN
https://developer.nvidia.com/cudnn-downloads
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
v1.2 (All-in-One)
Release Notes 發布內容
-
Add LLM models "gemini-1.5-flash-latest", "gemini-1.5-flash", and "gemini-1.5-pro".
新增LLM模型"gemini-1.5-flash-latest"、"gemini-1.5-flash"、"gemini-1.5-pro" -
Adjust the order of the LLM model selection menu.
調整LLM模型選單排序 -
Add the response time of each API in the CMD program execution log.
新增CMD程式運行紀錄中，各API響應時間
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
Note! The CUDA Toolkit and cuDNN are not included and must be installed independently.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
注意! CUDA Toolkit與cuDNN需自行安裝
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/1Mb_QO6-d0T49tUyO0z1iTuUoW_LBE0tP1yrWjq3ItqY/edit?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx?lang=tw
CUDA Toolkit
https://developer.nvidia.com/cuda-12-1-1-download-archive
cuDNN
https://developer.nvidia.com/cudnn-downloads
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
v1.1 (All-in-One)
Release Notes 發布內容
-
Fix the model selection function in VTSP Sentiment_Analysis.
修正VTSP Sentiment_Analysis選擇模型功能 -
Add LLM models "gpt-4o" and "gpt-4o-2024-05-13".
新增LLM模型"gpt-4o"、"gpt-4o-2024-05-13"
All-in-One Version 整合包
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
Note! The CUDA Toolkit and cuDNN are not included and must be installed independently.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
注意! CUDA Toolkit與cuDNN需自行安裝
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/1gOsWXmP24_Yd4k0MhQCqULVvIcJkMXKj7Jxq-Ggveds/edit?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx?lang=tw
CUDA Toolkit
https://developer.nvidia.com/cuda-12-1-1-download-archive
cuDNN
https://developer.nvidia.com/cudnn-downloads
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
v1.0 (All-in-One)
Release Notes 發布內容
This is the packaged version of the AI-VTuber-System including the required Python environment.
To run the program, simply click the AI-VTuber-System.bat file in the root directory.
Note! The CUDA Toolkit and cuDNN are not included and must be installed independently.
For more detailed instructions, please watch the video link provided below.
This version only includes the base model of whisper.
Download links for other models are provided below.
這是AI-VTuber-System含所需的python環境打包版
點擊根目錄下的AI-VTuber-System.bat即可運行程式
注意! CUDA Toolkit與cuDNN需自行安裝
更詳細的使用說明請觀看以下影片連結
此版本只包含whisper的base模型
其餘模型下方有下載連結
Tutorial Video 使用說明影片
https://www.youtube.com/watch?v=Hwss_p2Iroc
User Manual 使用手冊
https://docs.google.com/document/d/1D_XpNtdUKeGhDjovJ1mXINySTuz18nAk6MzUnJ5Rnvo/edit?usp=sharing
Nvidia
GPU Driver 顯示卡驅動程式
https://www.nvidia.com.tw/Download/index.aspx?lang=tw
CUDA Toolkit
https://developer.nvidia.com/cuda-12-1-1-download-archive
cuDNN
https://developer.nvidia.com/cudnn-downloads
Whisper Model Download Links 模型載點
tiny.en: https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
tiny: https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
base.en: https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
base: https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
small.en: https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
small: https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
medium.en: https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
medium: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
large-v1: https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
large-v2: https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
large-v3: https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt