docs: update default config

Author: timerring

README.md

@@ -188,7 +188,7 @@ MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关
 
 #### 4. bilitool 登录
 
-> 由于一般日志打印不出二维码效果（docker 的日志不确定是否能打印，等发布新image时再修改，docker 版本请先参考文档[bilive](https://bilive.timerring.com)，本 README 只针对源码部署），所以这步需要提前在机器上安装 [bilitool](https://github.com/timerring/bilitool):
+> 由于一般日志打印不出二维码效果（docker 的日志不确定是否能打印，等发布新image时再修改，docker 版本请先参考文档 [bilive](https://bilive.timerring.com)，本 README 只针对源码部署），所以这步需要提前在机器上安装 [bilitool](https://github.com/timerring/bilitool):
 
 ```
 pip install bilitool

src/config.py

@@ -10,12 +10,15 @@
 GPU_EXIST=True
 # Can be pipeline, append, merge
 MODEL_TYPE = "append"
+
 # =============== The auto speech recognition configuration ============================
-ASR_METHOD = "api" # can be "deploy" or "api" or "none"
+ASR_METHOD = "none" # can be "deploy" or "api" or "none"
 # If you choose "api", due to the limitation of free tier, you should keep every video less than 30 minutes(around)
 # Apply for your own API key at https://console.groq.com/keys
 WHISPER_API_KEY = ""
+# If you choose "deploy", you should download the model from https://huggingface.co/openai/whisper-large-v3-turbo
 Inference_Model = "small" # the model to be deployed
+
 # =============== The video configuration ============================
 TITLE = "{artist}直播回放-{date}-{title}" 
 # You can change the title as you like, eg.
@@ -25,6 +28,7 @@
 # You can change the description as you like.
 GIFT_PRICE_FILTER = 1 # The gift whose price is less than this value will be filtered, unit: RMB
 RESERVE_FOR_FIXING = False # If encounter MOOV crash error, delete the video or reserve for fixing
+
 # ============================ The video slice configuration ==================
 AUTO_SLICE = False
 SLICE_DURATION = 60 # better not exceed 300 seconds