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