From e950a921736eff5a547e7f53eb534c6ab5ecf86e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 19 十月 2023 14:27:22 +0800
Subject: [PATCH] docs

---
 egs_modelscope/asr/TEMPLATE/README.md    |    2 ++
 egs_modelscope/asr/TEMPLATE/README_zh.md |    1 +
 2 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index b9c4527..ae81e57 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -38,10 +38,12 @@
                                 batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
 print(rec_result)
 ```
+
 Where, 
 - `batch_size_token` refs to dynamic batch_size and the total tokens of batch is `batch_size_token`, 1 token = 60 ms. 
 - `batch_size_token_threshold_s`: The batch_size is set to 1, when the audio duration exceeds the threshold value of `batch_size_token_threshold_s`, specified in `s`.
 - `max_single_segment_time`: The maximum length for audio segmentation in VAD, specified in `ms`.
+
 Suggestion: When encountering OOM (Out of Memory) issues with long audio inputs, as the GPU memory usage increases with the square of the audio duration, there are three possible scenarios:
 
 a) In the initial inference stage, GPU memory usage primarily depends on `batch_size_token`. Reducing this value appropriately can help reduce memory usage.
diff --git a/egs_modelscope/asr/TEMPLATE/README_zh.md b/egs_modelscope/asr/TEMPLATE/README_zh.md
index 40e0731..67b49b5 100644
--- a/egs_modelscope/asr/TEMPLATE/README_zh.md
+++ b/egs_modelscope/asr/TEMPLATE/README_zh.md
@@ -42,6 +42,7 @@
 - `batch_size_token` 琛ㄧず閲囩敤鍔ㄦ�乥atch锛宐atch涓�籺oken鏁颁负 `batch_size_token`锛�1 token = 60 ms. 
 - `batch_size_token_threshold_s`: 琛ㄧず闊抽鏃堕暱瓒呰繃 `batch_size_token_threshold_s`闃堝�兼槸锛宐atch鏁拌缃负1, 鍗曚綅涓簊.
 - `max_single_segment_time`: 琛ㄧずVAD鏈�澶у垏鍓查煶棰戞椂闀�, 鍗曚綅鏄痬s.
+
 寤鸿锛氬綋鎮ㄨ緭鍏ヤ负闀块煶棰戯紝閬囧埌OOM闂鏃讹紝鍥犱负鏄惧瓨鍗犵敤涓庨煶棰戞椂闀垮憟骞虫柟鍏崇郴澧炲姞锛屽垎涓�3绉嶆儏鍐碉細
 - a)鎺ㄧ悊璧峰闃舵锛屾樉瀛樹富瑕佸彇鍐充簬`batch_size_token`锛岄�傚綋鍑忓皬璇ュ�硷紝鍙互鍑忓皯鏄惧瓨鍗犵敤锛�
 - b)鎺ㄧ悊涓棿闃舵锛岄亣鍒癡AD鍒囧壊鐨勯暱闊抽鐗囨锛屾�籺oken鏁板皬浜巂batch_size_token`锛屼粛鐒跺嚭鐜癘OM锛屽彲浠ラ�傚綋鍑忓皬`batch_size_token_threshold_s`锛岃秴杩囬槇鍊硷紝寮哄埗batch涓�1; 

--
Gitblit v1.9.1