8 lines
4.7 KiB
JSON
8 lines
4.7 KiB
JSON
{"id": "corr-time-01", "transcript": "set alarm for 6 i mean 7", "words": [{"text": "set", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "alarm", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "for", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "6", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "i", "start_s": 0.8, "end_s": 0.9, "prob": 0.9}, {"text": "mean", "start_s": 1.0, "end_s": 1.1, "prob": 0.9}, {"text": "7", "start_s": 1.2, "end_s": 1.3, "prob": 0.9}], "expected_aligned_text": "set alarm for 7", "expected": {"applied_min": 1, "required_rule_ids": ["cue_correction"], "forbidden_rule_ids": []}, "tags": ["i_mean_correction", "timing_sensitive"]}
|
|
{"id": "corr-time-gap-01", "transcript": "set alarm for 6 i mean 7", "words": [{"text": "set", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "alarm", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "for", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "6", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "i", "start_s": 2.0, "end_s": 2.1, "prob": 0.9}, {"text": "mean", "start_s": 2.2, "end_s": 2.3, "prob": 0.9}, {"text": "7", "start_s": 2.4, "end_s": 2.5, "prob": 0.9}], "expected_aligned_text": "set alarm for 6 i mean 7", "expected": {"applied_min": 0, "required_rule_ids": [], "forbidden_rule_ids": ["cue_correction"]}, "tags": ["i_mean_literal", "timing_sensitive"]}
|
|
{"id": "literal-mean-01", "transcript": "write exactly i mean this sincerely", "words": [{"text": "write", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "exactly", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "i", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "mean", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "this", "start_s": 0.8, "end_s": 0.9, "prob": 0.9}, {"text": "sincerely", "start_s": 1.0, "end_s": 1.1, "prob": 0.9}], "expected_aligned_text": "write exactly i mean this sincerely", "expected": {"applied_min": 0, "required_rule_ids": [], "forbidden_rule_ids": ["cue_correction"]}, "tags": ["i_mean_literal"]}
|
|
{"id": "restart-01", "transcript": "please send it please send it", "words": [{"text": "please", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "send", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "it", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "please", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "send", "start_s": 0.8, "end_s": 0.9, "prob": 0.9}, {"text": "it", "start_s": 1.0, "end_s": 1.1, "prob": 0.9}], "expected_aligned_text": "please send it", "expected": {"applied_min": 1, "required_rule_ids": ["restart_repeat"], "forbidden_rule_ids": []}, "tags": ["restart"]}
|
|
{"id": "actually-correction-01", "transcript": "set alarm for 6 actually 7", "words": [{"text": "set", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "alarm", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "for", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "6", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "actually", "start_s": 0.8, "end_s": 0.9, "prob": 0.9}, {"text": "7", "start_s": 1.0, "end_s": 1.1, "prob": 0.9}], "expected_aligned_text": "set alarm for 7", "expected": {"applied_min": 1, "required_rule_ids": ["cue_correction"], "forbidden_rule_ids": []}, "tags": ["actually_correction"]}
|
|
{"id": "sorry-correction-01", "transcript": "set alarm for 6 sorry 7", "words": [{"text": "set", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "alarm", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "for", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "6", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "sorry", "start_s": 0.8, "end_s": 0.9, "prob": 0.9}, {"text": "7", "start_s": 1.0, "end_s": 1.1, "prob": 0.9}], "expected_aligned_text": "set alarm for 7", "expected": {"applied_min": 1, "required_rule_ids": ["cue_correction"], "forbidden_rule_ids": []}, "tags": ["sorry_correction"]}
|
|
{"id": "no-correction-phrase-01", "transcript": "set alarm for 6 i mean", "words": [{"text": "set", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "alarm", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}, {"text": "for", "start_s": 0.4, "end_s": 0.5, "prob": 0.9}, {"text": "6", "start_s": 0.6, "end_s": 0.7, "prob": 0.9}, {"text": "i", "start_s": 0.8, "end_s": 0.9, "prob": 0.9}, {"text": "mean", "start_s": 1.0, "end_s": 1.1, "prob": 0.9}], "expected_aligned_text": "set alarm for 6 i mean", "expected": {"applied_min": 0, "required_rule_ids": [], "forbidden_rule_ids": ["cue_correction"]}, "tags": ["i_mean_literal"]}
|
|
{"id": "baseline-unchanged-01", "transcript": "hello world", "words": [{"text": "hello", "start_s": 0.0, "end_s": 0.1, "prob": 0.9}, {"text": "world", "start_s": 0.2, "end_s": 0.3, "prob": 0.9}], "expected_aligned_text": "hello world", "expected": {"applied_min": 0, "required_rule_ids": [], "forbidden_rule_ids": []}, "tags": ["baseline"]}
|