From b06c980504e195049e55492caa7535c329b91044 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 七月 2023 10:30:38 +0800
Subject: [PATCH] bugfix long wav batch_size_token_threshold_ms
---
funasr/bin/asr_inference_launch.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index edb4ad6..fd47047 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -566,7 +566,7 @@
hotword_list_or_file = kwargs['hotword']
speech2vadsegment.vad_model.vad_opts.max_single_segment_time = kwargs.get("max_single_segment_time", 60000)
- batch_size_token_threshold_ms = kwargs.get("batch_size_token_threshold_ms", int(speech2vadsegment.vad_model.vad_opts.max_single_segment_time*0.67))
+ batch_size_token_threshold_s = kwargs.get("batch_size_token_threshold_s", int(speech2vadsegment.vad_model.vad_opts.max_single_segment_time*0.67/1000)) * 1000
batch_size_token = kwargs.get("batch_size_token", 6000)
print("batch_size_token: ", batch_size_token)
@@ -649,7 +649,7 @@
beg_idx = 0
for j, _ in enumerate(range(0, n)):
batch_size_token_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
- if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_ms and (sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_threshold_ms:
+ if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_ms and (sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_threshold_s:
continue
batch_size_token_ms_cum = 0
end_idx = j + 1
--
Gitblit v1.9.1