From fe588bc508c0076bb007d6ed36c18ac8ecb341ac Mon Sep 17 00:00:00 2001
From: 王梦迪 <73778524+di-osc@users.noreply.github.com>
Date: 星期二, 20 五月 2025 16:10:59 +0800
Subject: [PATCH] Fsmn_vad支持多线程并发调用 (#2519)
---
funasr/models/sense_voice/model.py | 7 ++++++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 7971cc1..c5d0e59 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -925,6 +925,11 @@
if tok_ls: token_ids.extend(tok_ls)
else: token_ids.append(124)
+ if len(token_ids) == 0:
+ result_i = {"key": key[i], "text": text}
+ results.append(result_i)
+ continue
+
logits_speech = self.ctc.softmax(encoder_out)[i, 4 : encoder_out_lens[i].item(), :]
pred = logits_speech.argmax(-1).cpu()
logits_speech[pred == self.blank_id, self.blank_id] = 0
@@ -970,7 +975,7 @@
elif word.startswith("鈻�"):
word = word[1:]
timestamp_new.append([start, end])
- elif prev_word.isalpha() and prev_word.isascii() and word.isalpha() and word.isascii():
+ elif prev_word is not None and prev_word.isalpha() and prev_word.isascii() and word.isalpha() and word.isascii():
prev_word += word
timestamp_new[-1][1] = end
else:
--
Gitblit v1.9.1