Skip to content

Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.

docs: update readme

沈浩91f4d6164ef9
diff --git a/README.md b/README.md
index 292c1b65..73b56e32 100644
--- a/README.md
+++ b/README.md
@@ -86,7 +86,7 @@ https://github.com/user-attachments/assets/0b32fad3-c3ad-4b6a-abf0-0865f0dd2385
* `transcription_provider`和`llm_provider`都选择`openai`,这样在下方`openai`、`local_model`、`aliyun`三个配置项大类里只需要填写`openai.apikey`就可以进行字幕翻译。(`app.proxy`和`openai.base_url`按自己情况选填)
使用本地语言识别模型(暂不支持macOS)的配置方式(兼顾成本、速度与质量的选择)
-* `transcription_provider`填写`local_model`,`llm_provider`填写`openai`,这样在下方`openai`、`local_model`三个配置项大类里只需要填写`openai.apikey`和`local_model.faster_whisper`就可以进行字幕翻译,本地模型会自动下载。(`app.proxy`和`openai.base_url`同上)
+* `transcription_provider`填写`fasterwhisper`,`llm_provider`填写`openai`,这样在下方`openai`、`local_model`三个配置项大类里只需要填写`openai.apikey`和`local_model.faster_whisper`就可以进行字幕翻译,本地模型会自动下载。(`app.proxy`和`openai.base_url`同上)
以下几种使用情况,需要进行阿里云的配置:
* 如果`llm_provider`填写了`aliyun`,需要使用阿里云的大模型服务,因此需要配置`aliyun.bailian`项的配置
diff --git a/config/config-example.toml b/config/config-example.toml
index d520c222..f37d1dc3 100644
--- a/config/config-example.toml
+++ b/config/config-example.toml
@@ -1,5 +1,5 @@
[app]
- segment_duration = 5 # 音频分割间隔,单位:分钟,建议值:5-10
+ segment_duration = 5 # 音频切分处理间隔,单位:分钟,建议值:5-10,如果视频中话语较少可以适当提高
translate_parallel_num = 5 # 并发进行模型转录和翻译的数量上限,建议值:5,如果使用了本地模型,该项自动不生效
proxy = "" # 网络代理地址,格式如http://127.0.0.1:7890,可不填
transcribe_provider = "openai" # 语音识别,当前可选值:openai,fasterwhisper,aliyun。fasterwhisper不支持macOS
diff --git a/docs/README_en.md b/docs/README_en.md
index ea030689..a015b3f7 100644
--- a/docs/README_en.md
+++ b/docs/README_en.md
@@ -80,7 +80,7 @@ The quickest and most convenient configuration method:
* Select `openai` for both `transcription_provider` and `llm_provider`. In this way, you only need to fill in `openai.apikey` in the following three major configuration item categories, namely `openai`, `local_model`, and `aliyun`, and then you can conduct subtitle translation. (Fill in `app.proxy` and `openai.base_url` as per your own situation.)
The configuration method for using the local speech recognition model (macOS is not supported for the time being) (a choice that takes into account cost, speed, and quality):
-* Fill in `local_model` for `transcription_provider` and `openai` for `llm_provider`. In this way, you only need to fill in `openai.apikey` and `local_model.faster_whisper` in the following three major configuration item categories, namely `openai` and `local_model`, and then you can conduct subtitle translation. The local model will be downloaded automatically. (The same applies to `app.proxy` and `openai.base_url` as mentioned above.)
+* Fill in `fasterwhisper` for `transcription_provider` and `openai` for `llm_provider`. In this way, you only need to fill in `openai.apikey` and `local_model.faster_whisper` in the following three major configuration item categories, namely `openai` and `local_model`, and then you can conduct subtitle translation. The local model will be downloaded automatically. (The same applies to `app.proxy` and `openai.base_url` as mentioned above.)
The following usage situations require the configuration of Alibaba Cloud:
* If `llm_provider` is filled with `aliyun`, it indicates that the large model service of Alibaba Cloud will be used. Consequently, the configuration of the `aliyun.bailian` item needs to be set up.
diff --git a/docs/aliyun.md b/docs/aliyun.md
index e3131ed8..551c31d1 100644
--- a/docs/aliyun.md
+++ b/docs/aliyun.md
@@ -21,4 +21,14 @@
4. 复制app key即可
![阿里云speech](images/aliyun_speech_3.png)
-## 阿里云OSS服务开通
\ No newline at end of file
+## 阿里云OSS服务开通
+1. 进入[阿里云对象存储服务控制台](https://oss.console.aliyun.com/overview),首次进入需开通服务
+2. 左侧选择Bucket列表,然后点击创建
+![阿里云OSS](./images/aliyun_oss_1.png)
+3. 选择快捷创建,填写合适的名字和就近的地域,完成创建(此处填写的名字就是配置项`aliyun.oss.bucket`的值)
+![阿里云OSS](./images/aliyun_oss_2.png)
+4. 创建完成后进入Bucket
+![阿里云OSS](./images/aliyun_oss_3.png)
+5. 将“阻止公共访问”开关关闭,并设置读写权限为“公共读”
+![阿里云OSS](./images/aliyun_oss_4.png)
+![阿里云OSS](./images/aliyun_oss_5.png)
\ No newline at end of file
diff --git a/docs/images/aliyun_oss_1.png b/docs/images/aliyun_oss_1.png
new file mode 100644
index 00000000..0fde7b46
Binary files /dev/null and b/docs/images/aliyun_oss_1.png differ
diff --git a/docs/images/aliyun_oss_2.png b/docs/images/aliyun_oss_2.png
new file mode 100644
index 00000000..79b56f82
Binary files /dev/null and b/docs/images/aliyun_oss_2.png differ
diff --git a/docs/images/aliyun_oss_3.png b/docs/images/aliyun_oss_3.png
new file mode 100644
index 00000000..ca50bb82
Binary files /dev/null and b/docs/images/aliyun_oss_3.png differ
diff --git a/docs/images/aliyun_oss_4.png b/docs/images/aliyun_oss_4.png
new file mode 100644
index 00000000..058c65b8
Binary files /dev/null and b/docs/images/aliyun_oss_4.png differ
diff --git a/docs/images/aliyun_oss_5.png b/docs/images/aliyun_oss_5.png
new file mode 100644
index 00000000..486d641f
Binary files /dev/null and b/docs/images/aliyun_oss_5.png differ