From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/models/sense_voice/model.py | 12 +++++++++---
1 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 945a301..bd1c76d 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -919,14 +919,20 @@
timestamp = []
tokens = tokenizer.text2tokens(text)[4:]
+ token_back_to_id = tokenizer.tokens2ids(tokens)
+ token_ids = []
+ for tok_ls in token_back_to_id:
+ if tok_ls: token_ids.extend(tok_ls)
+ else: token_ids.append(124)
+
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
align = ctc_forced_align(
logits_speech.unsqueeze(0).float(),
- torch.Tensor(token_int[4:]).unsqueeze(0).long().to(logits_speech.device),
+ torch.Tensor(token_ids).unsqueeze(0).long().to(logits_speech.device),
(encoder_out_lens[i] - 4).long(),
- torch.tensor(len(token_int) - 4).unsqueeze(0).long().to(logits_speech.device),
+ torch.tensor(len(token_ids)).unsqueeze(0).long().to(logits_speech.device),
ignore_id=self.ignore_id,
)
pred = groupby(align[0, : encoder_out_lens[i]])
@@ -964,7 +970,7 @@
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