rm vad dataset

.gitignore

@@ -0,0 +1 @@
+**/__pycache__

vad/dataset/transcripts/test1_segment_1_20250423_130738.json → dataset/transcripts/test1_segment_1_20250423_161502.json

@@ -1,11 +1,11 @@
 {
   "audio_file": "dataset/audio/segments\\test1_segment_1.wav",
-  "timestamp": "20250423_130738",
+  "timestamp": "20250423_161502",
   "segments": [
     {
       "text": "音频数据处理",
-      "start_time": 0.0,
-      "end_time": 1.16,
+      "start_time": 4.56,
+      "end_time": 5.72,
       "confidence": 0.906494140625,
       "verified": false,
       "verified_text": null,
@@ -13,8 +13,8 @@
     },
     {
       "text": "所有音频或语言相关的任务都需要使用音频",
-      "start_time": 0.0,
-      "end_time": 3.72,
+      "start_time": 8.4,
+      "end_time": 12.120000000000001,
       "confidence": 0.7564697265625,
       "verified": false,
       "verified_text": null,
@@ -22,8 +22,8 @@
     },
     {
       "text": "在我们先入了解这些任务之前",
-      "start_time": 0.0,
-      "end_time": 1.6400000000000001,
+      "start_time": 13.11,
+      "end_time": 14.75,
       "confidence": 0.939605712890625,
       "verified": false,
       "verified_text": null,
@@ -31,8 +31,8 @@
     },
     {
       "text": "我们需要了解音频文件的实际内容",
-      "start_time": 1.6400000000000001,
-      "end_time": 4.0,
+      "start_time": 14.75,
+      "end_time": 17.11,
       "confidence": 0.939605712890625,
       "verified": false,
       "verified_text": null,
@@ -40,8 +40,8 @@
     },
     {
       "text": "以及如何",
-      "start_time": 4.0,
-      "end_time": 4.8,
+      "start_time": 17.11,
+      "end_time": 17.91,
       "confidence": 0.939605712890625,
       "verified": false,
       "verified_text": null,
@@ -49,8 +49,8 @@
     },
     {
       "text": "本台語言將為你介紹的",
-      "start_time": 0.0,
-      "end_time": 1.28,
+      "start_time": 19.77,
+      "end_time": 21.05,
       "confidence": 0.907470703125,
       "verified": false,
       "verified_text": null,
@@ -58,8 +58,8 @@
     },
     {
       "text": "本单元将为你介绍于音频数据相关的基本概念",
-      "start_time": 0.0,
-      "end_time": 3.92,
+      "start_time": 21.63,
+      "end_time": 25.549999999999997,
       "confidence": 0.66796875,
       "verified": false,
       "verified_text": null,
@@ -67,8 +67,8 @@
     },
     {
       "text": "包括剝形、採用、綠和平補土",
-      "start_time": 0.0,
-      "end_time": 2.0,
+      "start_time": 26.28,
+      "end_time": 28.28,
       "confidence": 0.708251953125,
       "verified": false,
       "verified_text": null,
@@ -76,8 +76,8 @@
     },
     {
       "text": "你會學習到如何使用音頻",
-      "start_time": 2.0,
-      "end_time": 3.6,
+      "start_time": 28.28,
+      "end_time": 29.880000000000003,
       "confidence": 0.708251953125,
       "verified": false,
       "verified_text": null,
@@ -85,8 +85,8 @@
     },
     {
       "text": "包括音频数位加载",
-      "start_time": 0.0,
-      "end_time": 1.4000000000000001,
+      "start_time": 30.42,
+      "end_time": 31.82,
       "confidence": 0.86474609375,
       "verified": false,
       "verified_text": null,
@@ -94,8 +94,8 @@
     },
     {
       "text": "音频数据处理",
-      "start_time": 1.4000000000000001,
-      "end_time": 2.4,
+      "start_time": 31.82,
+      "end_time": 32.82,
       "confidence": 0.86474609375,
       "verified": false,
       "verified_text": null,
@@ -103,8 +103,8 @@
     },
     {
       "text": "高效加载大规模音频数级的流适加载方",
-      "start_time": 0.0,
-      "end_time": 2.88,
+      "start_time": 33.54,
+      "end_time": 36.42,
       "confidence": 0.956787109375,
       "verified": false,
       "verified_text": null,
@@ -112,8 +112,8 @@
     },
     {
       "text": "完成本單元的學期後",
-      "start_time": 0.0,
-      "end_time": 1.44,
+      "start_time": 37.8,
+      "end_time": 39.239999999999995,
       "confidence": 0.9926719665527344,
       "verified": false,
       "verified_text": null,
@@ -121,8 +121,8 @@
     },
     {
       "text": "你會找",
-      "start_time": 1.44,
-      "end_time": 2.12,
+      "start_time": 39.239999999999995,
+      "end_time": 39.919999999999995,
       "confidence": 0.9926719665527344,
       "verified": false,
       "verified_text": null,
@@ -130,8 +130,8 @@
     },
     {
       "text": "基础的音频相关数",
-      "start_time": 0.0,
-      "end_time": 1.6,
+      "start_time": 40.86,
+      "end_time": 42.46,
       "confidence": 0.7969970703125,
       "verified": false,
       "verified_text": null,
@@ -139,8 +139,8 @@
     },
     {
       "text": "并且掌握针对不同应用的音频数据处理工具",
-      "start_time": 0.0,
-      "end_time": 3.52,
+      "start_time": 43.05,
+      "end_time": 46.57,
       "confidence": 0.9851303100585938,
       "verified": false,
       "verified_text": null,
@@ -148,8 +148,8 @@
     },
     {
       "text": "本单元的支持会成为后面章节的",
-      "start_time": 0.0,
-      "end_time": 2.0,
+      "start_time": 47.49,
+      "end_time": 49.49,
       "confidence": 0.930908203125,
       "verified": false,
       "verified_text": null,

vad/audio_transcriber.py

@@ -63,7 +63,7 @@ class AudioTranscriber:
     def save_transcription(self, 
                          results: List[TranscriptionResult], 
                          audio_path: str,
-                         output_dir: str = "../dataset/transcripts"):
+                         output_dir: str = "dataset/transcripts"):
         """
         保存转录结果到JSON文件
         """

vad/dataset/audio/segments/test1_segment_1.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:877aee33d778b34af2f0b819ac822d80316e97b73cb3823c1f436dbef8efcb0e
-size 35564

vad/dataset/audio/segments/test1_segment_10.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3135d983a5260d846e6cf165583efa3a0ef379bd86c885e678a63b41f66f548b
-size 48044

vad/dataset/audio/segments/test1_segment_11.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a966cbb2e82ebd278692adad509a18061306b73b715fc4a93468c27ed61627b
-size 111404

vad/dataset/audio/segments/test1_segment_12.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52cfbcdc17cc5f190df467310f1a91c89e27f79662b2ce13f4ff5ec07015afec
-size 71084

vad/dataset/audio/segments/test1_segment_13.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8eedb04a2d817c0875003a7594f8bac255a28898dfae56aa97bd3021870140b2
-size 86444

vad/dataset/audio/segments/test1_segment_14.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:078850683b71e5b04781884b44bce0edb74999459b68b6fd53175ecacbd4980e
-size 34604

vad/dataset/audio/segments/test1_segment_15.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c9c467e2ec3bdec346774cde0480a78689c0f6f13fd093b32baaa00187c392fb
-size 29804

vad/dataset/audio/segments/test1_segment_16.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:59bc62b5c124c9cac5ef78c69caff4e5caf3d0333e496e382ee365142eafc354
-size 47084

vad/dataset/audio/segments/test1_segment_17.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2dbcb3578c8537243143da7ac2c7531ea7b9fc750cb26e9809643289eeddce7b
-size 107564

vad/dataset/audio/segments/test1_segment_18.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:538b2dda6990368d68234fded22b5ed3d67c56a620e79cba7ac545a102465160
-size 68204

vad/dataset/audio/segments/test1_segment_2.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:81375721eb3a532941083c9781f53f5e0f1ccbe1ef4108f98a019de400f5c564
-size 117164

vad/dataset/audio/segments/test1_segment_3.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd6120ff04e7365640b9e3a1fb062bc1c31ce0dc54904bd27e25ac5a0b068cde
-size 149804

vad/dataset/audio/segments/test1_segment_4.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:99bc0d18ffd0d10742b8d6b5450e537eccd1497c2247e714fa8efe6beb602abd
-size 41324

vad/dataset/audio/segments/test1_segment_5.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a9e2196db3537028898b87442f074523251b33219302e6eb8518fb33396c30bd
-size 122924

vad/dataset/audio/segments/test1_segment_6.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e929f7966a425a559b7442a2914cb99b0df74f1d02938264642dc71f160fc383
-size 113324

vad/dataset/audio/segments/test1_segment_7.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65d800356647c415d80e59fac63db01df31ce51a497aacf43f98aa0e6ec468cb
-size 77804

vad/dataset/audio/segments/test1_segment_8.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1c574a7c20332f85c6260febf6eae232473a798404ca29f1b54ac39e5b2d35c
-size 91244

vad/dataset/audio/segments/test1_segment_9.wav

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f943b20eb3aafa0befb884f5d125e0596d3f419d8a3c5546ff3cf878603c36b8
-size 67244

vad/dataset/audio/temp/test1_segments_20250423_114118.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_114118",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}

vad/dataset/audio/temp/test1_segments_20250423_114230.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_114230",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}

vad/dataset/audio/temp/test1_segments_20250423_114252.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_114252",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}

vad/dataset/audio/temp/test1_segments_20250423_125721.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_125721",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}

vad/dataset/audio/temp/test1_segments_20250423_130157.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_130157",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}

vad/dataset/audio/temp/test1_segments_20250423_130617.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_130617",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}

vad/dataset/audio/temp/test1_segments_20250423_130734.json

@@ -1,80 +0,0 @@
-{
-  "audio_file": "../dataset/audio/test1.wav",
-  "timestamp": "20250423_130734",
-  "total_frames": 1821,
-  "speech_frames": 1167,
-  "segments": [
-    {
-      "start_time": 4.56,
-      "end_time": 5.67,
-      "duration": 1.1100000000000003,
-      "is_speech": true
-    },
-    {
-      "start_time": 8.4,
-      "end_time": 12.06,
-      "duration": 3.66,
-      "is_speech": true
-    },
-    {
-      "start_time": 13.11,
-      "end_time": 17.79,
-      "duration": 4.68,
-      "is_speech": true
-    },
-    {
-      "start_time": 19.77,
-      "end_time": 21.06,
-      "duration": 1.2899999999999991,
-      "is_speech": true
-    },
-    {
-      "start_time": 21.63,
-      "end_time": 25.47,
-      "duration": 3.84,
-      "is_speech": true
-    },
-    {
-      "start_time": 26.28,
-      "end_time": 29.82,
-      "duration": 3.539999999999999,
-      "is_speech": true
-    },
-    {
-      "start_time": 30.42,
-      "end_time": 32.85,
-      "duration": 2.4299999999999997,
-      "is_speech": true
-    },
-    {
-      "start_time": 33.54,
-      "end_time": 36.39,
-      "duration": 2.8500000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 37.8,
-      "end_time": 39.9,
-      "duration": 2.1000000000000014,
-      "is_speech": true
-    },
-    {
-      "start_time": 40.86,
-      "end_time": 42.36,
-      "duration": 1.5,
-      "is_speech": true
-    },
-    {
-      "start_time": 43.05,
-      "end_time": 46.53,
-      "duration": 3.480000000000004,
-      "is_speech": true
-    },
-    {
-      "start_time": 47.49,
-      "end_time": 49.71,
-      "duration": 2.219999999999999,
-      "is_speech": true
-    }
-  ]
-}