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 | 30 +++++++++++++++++++++---------
1 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 70cd02e..bd1c76d 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -919,17 +919,23 @@
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),
- (encoder_out_lens - 4).long(),
- torch.tensor(len(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_ids)).unsqueeze(0).long().to(logits_speech.device),
ignore_id=self.ignore_id,
)
- pred = groupby(align[0, : encoder_out_lens[0]])
+ pred = groupby(align[0, : encoder_out_lens[i]])
_start = 0
token_id = 0
ts_max = encoder_out_lens[i] - 4
@@ -951,20 +957,26 @@
def post(self, timestamp):
timestamp_new = []
+ prev_word = None
for i, t in enumerate(timestamp):
word, start, end = t
+ start = int(start * 1000)
+ end = int(end * 1000)
if word == "鈻�":
continue
if i == 0:
# timestamp_new.append([word, start, end])
- timestamp_new.append([int(start * 1000), int(end * 1000)])
- elif word.startswith("鈻�") or len(word) == 1 or not word[1].isalpha():
+ timestamp_new.append([start, end])
+ elif word.startswith("鈻�"):
word = word[1:]
- # timestamp_new.append([word, start, end])
- timestamp_new.append([int(start * 1000), int(end * 1000)])
+ timestamp_new.append([start, end])
+ 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:
# timestamp_new[-1][0] += word
- timestamp_new[-1][1] = int(end * 1000)
+ timestamp_new.append([start, end])
+ prev_word = word
return timestamp_new
def export(self, **kwargs):
--
Gitblit v1.9.1