Spaces:
Sleeping
Sleeping
File size: 3,448 Bytes
50ad069 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
[
{
"id": "pause_pause1",
"input_path": "/input/pause/pause1.wav",
"text": "重复一遍“我一把/把把/把住了”这句话",
"task": "Pause and segmentation",
"task_description": "Can the model accurately pause and segment in ambiguous cases?",
"output_path_4o": "/output/ChatGPT-4o/pause/pause1/pause1.wav",
"output_path_miniomni": "/output/Mini-Omni/pause/00.wav",
"output_path_speechgpt": "/output/SpeechGPT/pause/pause1.wav",
"output_path_funaudio": "/output/FunAudioLLM/pause/audio_0.wav",
"language": "Chinese",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/pause/pause1.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/pause/pause1.wav",
"level": "L3"
},
{
"id": "pause_pause2",
"input_path": "/input/pause/pause2.wav",
"text": "“我一把/把把/把住了”你知道是什么意思吗？",
"task": "Pause and segmentation",
"task_description": "Can the model accurately pause and segment in ambiguous cases?",
"output_path_4o": "/output/ChatGPT-4o/pause/pause2/pause2.wav",
"output_path_miniomni": "/output/Mini-Omni/pause/01.wav",
"output_path_speechgpt": "/output/SpeechGPT/pause/pause2.wav",
"output_path_funaudio": "/output/FunAudioLLM/pause/audio_1.wav",
"language": "Chinese",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/pause/pause2.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/pause/pause2.wav",
"level": "L1"
},
{
"id": "pause_pause3",
"input_path": "/input/pause/pause3.wav",
"text": "你知道下面这句话是什么意思吗？“昨天晚上小偷/偷偷/偷了我的电脑。”，并用明显的停顿重复一遍。",
"task": "Pause and segmentation",
"task_description": "Can the model accurately pause and segment in ambiguous cases?",
"output_path_4o": "/output/ChatGPT-4o/pause/pause3/pause3.wav",
"output_path_miniomni": "/output/Mini-Omni/pause/02.wav",
"output_path_speechgpt": "/output/SpeechGPT/pause/pause3.wav",
"output_path_funaudio": "/output/FunAudioLLM/pause/audio_2.wav",
"language": "Chinese",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/pause/pause3.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/pause/pause3.wav",
"level": "L3"
},
{
"id": "pause_pause4",
"input_path": "/input/pause/pause4.wav",
"text": "下面第一个句子还是第二个句子的停顿是正确的？“南京市/长江大桥欢迎您’和‘南京市长/江大桥欢迎您’”",
"task": "Pause and segmentation",
"task_description": "Can the model accurately pause and segment in ambiguous cases?",
"output_path_4o": "/output/ChatGPT-4o/pause/pause4/pause4.wav",
"output_path_miniomni": "/output/Mini-Omni/pause/03.wav",
"output_path_speechgpt": "/output/SpeechGPT/pause/pause4.wav",
"output_path_funaudio": "/output/FunAudioLLM/pause/audio_3.wav",
"language": "Chinese",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/pause/pause4.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/pause/pause4.wav",
"level": "L1"
}
] |