From fa9a6cdb1eade68c258eed7297f5a8a8a5329ac6 Mon Sep 17 00:00:00 2001
From: Flute <41096447+fluteink@users.noreply.github.com>
Date: 星期三, 01 十月 2025 14:44:28 +0800
Subject: [PATCH] 更新文档和运行脚本，修复文档拼写错误 (#2688)
---
funasr/models/sense_voice/model.py | 46 ++++++++++++++++++++++++++++++++++------------
1 files changed, 34 insertions(+), 12 deletions(-)
diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 70cd02e..6a29181 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -919,17 +919,28 @@
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)
+
+ 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
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
@@ -941,8 +952,8 @@
timestamp.append([tokens[token_id], ts_left, ts_right])
token_id += 1
_start = _end
- timestamp = self.post(timestamp)
- result_i = {"key": key[i], "text": text, "timestamp": timestamp}
+ timestamp, words = self.post(timestamp)
+ result_i = {"key": key[i], "text": text, "timestamp": timestamp, "words": words}
results.append(result_i)
else:
result_i = {"key": key[i], "text": text}
@@ -951,21 +962,32 @@
def post(self, timestamp):
timestamp_new = []
+ words_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])
+ words_new.append(word)
+ 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])
+ words_new.append(word)
+ elif prev_word is not None and prev_word.isalpha() and prev_word.isascii() and word.isalpha() and word.isascii():
+ word = prev_word + word
+ timestamp_new[-1][1] = end
+ words_new[-1] = word
else:
# timestamp_new[-1][0] += word
- timestamp_new[-1][1] = int(end * 1000)
- return timestamp_new
+ timestamp_new.append([start, end])
+ words_new.append(word)
+ prev_word = word
+ return timestamp_new, words_new
def export(self, **kwargs):
from .export_meta import export_rebuild_model
--
Gitblit v1.9.1