From 8b0fb74bded1f8a162e6c0e94c3522be6216ea03 Mon Sep 17 00:00:00 2001
From: chengligen <101448376+chengligen@users.noreply.github.com>
Date: 星期一, 26 五月 2025 14:11:33 +0800
Subject: [PATCH] feat: add 'words' key aligned with timestamps in sensevoice model output (#2531)
---
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