From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
runtime/triton_gpu/client/speech_client.py | 4 +---
1 files changed, 1 insertions(+), 3 deletions(-)
diff --git a/runtime/triton_gpu/client/speech_client.py b/runtime/triton_gpu/client/speech_client.py
index 1bafbe2..15482a7 100644
--- a/runtime/triton_gpu/client/speech_client.py
+++ b/runtime/triton_gpu/client/speech_client.py
@@ -71,9 +71,7 @@
# the exact first chunk length frames
# since the subsampling will look ahead several frames
first_chunk_length = (chunk_size - 1) * subsampling + context
- add_frames = math.ceil(
- (frame_length_ms - frame_shift_ms) / frame_shift_ms
- )
+ add_frames = math.ceil((frame_length_ms - frame_shift_ms) / frame_shift_ms)
first_chunk_ms = (first_chunk_length + add_frames) * frame_shift_ms
other_chunk_ms = chunk_size * subsampling * frame_shift_ms
self.first_chunk_in_secs = first_chunk_ms / 1000
--
Gitblit v1.9.1