From bea5d984233aae08d7b9f6a3e8a3f309fae581ad Mon Sep 17 00:00:00 2001
From: dingbig <dingbig@gmail.com>
Date: 星期三, 22 二月 2023 19:48:50 +0800
Subject: [PATCH] Add sentence timestamp support
---
funasr/utils/timestamp_tools.py | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
funasr/bin/asr_inference_paraformer_vad_punc.py | 5 +++++
2 files changed, 57 insertions(+), 0 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index 408b5b9..a7ccfc2 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -47,6 +47,8 @@
from funasr.bin.punctuation_infer import Text2Punc
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
+from FunASR.funasr.utils.timestamp_tools import time_stamp_sentence
+
header_colors = '\033[95m'
end_colors = '\033[0m'
@@ -720,6 +722,7 @@
text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
text_postprocessed_punc = text_postprocessed
+ punc_id_list = []
if len(word_lists) > 0 and text2punc is not None:
text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
@@ -729,6 +732,8 @@
if time_stamp_postprocessed != "":
item['time_stamp'] = time_stamp_postprocessed
+ item['sentences'] = time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed)
+
asr_result_list.append(item)
finish_count += 1
# asr_utils.print_progress(finish_count / file_count)
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index 317c223..f6a6e98 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -54,3 +54,55 @@
res.append([int(timestamp[0] * 1000), int(timestamp[1] * 1000)])
return res
+def time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed):
+ res = []
+ if text_postprocessed is None:
+ return res
+ if time_stamp_postprocessed is None:
+ return res
+ if len(time_stamp_postprocessed) == 0:
+ return res
+ if len(text_postprocessed) == 0:
+ return res
+ if punc_id_list is None or len(punc_id_list) == 0:
+ res.append({
+ 'text': text_postprocessed.split(),
+ "start": time_stamp_postprocessed[0][0],
+ "end": time_stamp_postprocessed[-1][1]
+ })
+ return res
+ if len(punc_id_list) != len(time_stamp_postprocessed):
+ res.append({
+ 'text': text_postprocessed.split(),
+ "start": time_stamp_postprocessed[0][0],
+ "end": time_stamp_postprocessed[-1][1]
+ })
+ return res
+
+ sentence_text = ''
+ sentence_start = time_stamp_postprocessed[0][0]
+ texts = text_postprocessed.split()
+ for i in range(len(punc_id_list)):
+ sentence_text += texts[i]
+ if punc_id_list[i] == 2:
+ sentence_text += ','
+ res.append({
+ 'text': sentence_text,
+ "start": sentence_start,
+ "end": time_stamp_postprocessed[i][1]
+ })
+ sentence_text = ''
+ sentence_start = time_stamp_postprocessed[i][1]
+ elif punc_id_list[i] == 3:
+ sentence_text += '.'
+ res.append({
+ 'text': sentence_text,
+ "start": sentence_start,
+ "end": time_stamp_postprocessed[i][1]
+ })
+ sentence_text = ''
+ sentence_start = time_stamp_postprocessed[i][1]
+ return res
+
+
+
--
Gitblit v1.9.1