train_example.jsonl 4.3 KB

12345678910
  1. {"key": "YOU0000008470_S0000238_punc_itn", "text_language": "<|en|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|withitn|>", "target": "Including legal due diligence, subscription agreement, negotiation.", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/english_all/audio/YOU0000008470_S0000238.wav", "target_len": 7, "source_len": 140}
  2. {"key": "AUD0000001556_S0007580", "text_language": "<|en|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "there is a tendency to identify the self or take interest in what one has got used to", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/english_all/audio/AUD0000001556_S0007580.wav", "target_len": 18, "source_len": 360}
  3. {"key": "19208207_HJwKrcFJ8_o_segment720", "text_language": "<|en|>", "emo_target": "<|EMO_UNKNOWN|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "fourth foul up top now to austin three for leonard and in and out no good rebounded by murray looking for some help and he almost throws it out of bounds", "source": "/cpfs_speech/data/shared/Group-speech/beinian.lzr/data/multilingual/lcd_data/english/production/20240222/wer_0_5/taskid_19208207/wav/19208207_HJwKrcFJ8_o_segment720.wav", "target_len": 31, "source_len": 620}
  4. {"key": "wav000_0872_bb6f4a79bb9f49249083465445b1cafa_01c38131ed3a4c609e8270a09170525d", "text_language": "<|zh|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "案件受理费减半收取计一千六百三十一元赵会龙已预交由赵会龙负担一百零七元", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/16k_common/audio/wav000_0872_bb6f4a79bb9f49249083465445b1cafa_01c38131ed3a4c609e8270a09170525d.wav", "target_len": 35, "source_len": 700}
  5. {"key": "Speaker0244_iPhone_s0_227", "text_language": "<|ko|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "저녁 다 해결합니다", "source": "/cpfs_speech/data/shared/Group-speech/beinian.lzr/data/multilingual/korean/audio/Speaker0244_iPhone_s0_227.wav", "target_len": 10, "source_len": 200}
  6. {"key": "data2sim_speed_part1_channel0_CHANNEL0_SPEAKER0948_SESSION1_009481629_speed12", "text_language": "<|en|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "the money was entrust to him in february this year before he resign in june according to the documents", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/english_all/audio/data2sim_speed_part1_channel0_CHANNEL0_SPEAKER0948_SESSION1_009481629_speed12.wav", "target_len": 19, "source_len": 380}
  7. {"key": "SPEAKER0272_SESSION1_002721613_punc_itn", "text_language": "<|en|>", "emo_target": "<|EMO_UNKNOWN|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|withitn|>", "target": "Current proposals don't go far enough.", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/english_all/audio/SPEAKER0272_SESSION1_002721613.wav", "target_len": 6, "source_len": 120}
  8. {"key": "wav004_0490_04c4f9cb2cb347a2a156c5cad1a903aa", "text_language": "<|zh|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "小凳子", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/16k_common/audio/wav004_0490_04c4f9cb2cb347a2a156c5cad1a903aa.wav", "target_len": 3, "source_len": 60}
  9. {"key": "18874657_MSnA4nfDC7Q_segment680", "text_language": "<|en|>", "emo_target": "<|NEUTRAL|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "and anything that you would like to know please just put it in the email", "source": "/cpfs_speech/data/shared/Group-speech/beinian.lzr/data/multilingual/lcd_data/english/production/20240105/wer_0_5/taskid_18874657/wav/18874657_MSnA4nfDC7Q_segment680.wav", "target_len": 15, "source_len": 300}
  10. {"key": "POD0000007250_S0000518", "text_language": "<|en|>", "emo_target": "<|EMO_UNKNOWN|>", "event_target": "<|Speech|>", "with_or_wo_itn": "<|woitn|>", "target": "i use netflix but and that's not an app", "source": "/cpfs01/shared/Group-speech/beinian.lzr/data/industrial_data/english_all/audio/POD0000007250_S0000518.wav", "target_len": 9, "source_len": 180}