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 ++
1 files changed, 2 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.
--
Gitblit v1.9.1