From cf8e000a84e888495dcf30c4dbfecea1ee7ab4e2 Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 07 八月 2023 16:13:37 +0800
Subject: [PATCH] Merge pull request #807 from alibaba-damo-academy/dev_wjm

---
 funasr/bin/asr_inference_launch.py |    5 ++---
 1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 36c6d76..0fd5abd 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -260,8 +260,6 @@
         hotword_list_or_file = None
         clas_scale = 1.0
 
-    if kwargs.get("device", None) == "cpu":
-        ngpu = 0
     if ngpu >= 1 and torch.cuda.is_available():
         device = "cuda"
     else:
@@ -566,6 +564,7 @@
             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_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)
 
@@ -648,7 +647,7 @@
             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]) < speech2vadsegment.vad_model.vad_opts.max_single_segment_time:
+                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