File size: 7,466 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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
[
{
"id": "rhythm_audio_0",
"input_path": "/input/rhythm/audio_0.mp3",
"text": "Say the following sentence very slowly: \"The quick brown fox jumps over the lazy dog.\"",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/audio_0/audio_0.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/00.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/answer_0.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/audio_0.wav",
"text_cn": "非常缓慢地说以下句子：'快速的棕狐跳过了懒狗。",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/audio_0.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/audio_0.wav",
"level": "L2"
},
{
"id": "rhythm_audio_3",
"input_path": "/input/rhythm/audio_3.mp3",
"text": "Say the first half of this sentence quickly and the second half slowly: \"In a world full of challenges, we need to find creative solutions to make things better.\"",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/audio_3/audio_3.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/01.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/answer_3.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/audio_1.wav",
"text_cn": "在这句话的上半年中迅速和下半部分说：“在一个充满挑战的世界中，我们需要找到创造性的解决方案来使事情变得更好。",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/audio_3.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/audio_3.wav",
"level": "L2"
},
{
"id": "rhythm_audio_7",
"input_path": "/input/rhythm/audio_7.mp3",
"text": "First, say this sentence as fast as you can, then repeat it very slowly: \"The rain in Spain falls mainly in the plain.\"",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/audio_7/audio_7.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/02.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/answer_7.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/audio_2.wav",
"text_cn": "首先，尽可能快地说这句话，然后非常缓慢地重复：'西班牙的降雨主要落在平原上。",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/audio_7.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/audio_7.wav",
"level": "L2"
},
{
"id": "rhythm_audio_18",
"input_path": "/input/rhythm/audio_18.mp3",
"text": "Repeat the phrase 'Practice makes perfect' three times, each time at a different speed: first very slowly, then moderately, and finally very fast.",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/audio_18/audio_18.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/03.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/answer_18.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/audio_3.wav",
"text_cn": "每次以不同的速度重复三次“练习完美”一词：首先非常缓慢，然后适度，最后非常快。",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/audio_18.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/audio_18.wav",
"level": "L2"
},
{
"id": "rhythm_audio_22",
"input_path": "/input/rhythm/audio_22.mp3",
"text": "Say the following sentence as if you're whispering: \"This is a secret, you can't tell anyone.\"",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/audio_22/audio_22.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/04.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/answer_22.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/audio_4.wav",
"text_cn": "说以下句子，好像您在窃窃私语：“这是一个秘密，您不能告诉任何人。",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/audio_22.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/audio_22.wav",
"level": "L2"
},
{
"id": "rhythm_audio_23",
"input_path": "/input/rhythm/audio_23.mp3",
"text": "Repeat this sentence very loudly as if you are trying to get someone's attention: \"Watch out! There's something coming your way!\"",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/audio_23/audio_23.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/05.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/answer_23.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/audio_5.wav",
"text_cn": "大声重复这句话，好像您想引起某人的注意：“当心！有一些事情！",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/audio_23.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/audio_23.wav",
"level": "L2"
},
{
"id": "rhythm_input_audio_3",
"input_path": "/input/rhythm/input_audio_3.wav",
"text": "Say the following sentence at my speed first, then say it again very slowly: \"Artificial intelligence is changing the world in many ways.\"",
"task": "Rhythm control capabilities",
"task_description": "Can the model adjust the output pace, speaking faster or slower as required?",
"output_path_4o": "/output/ChatGPT-4o/rhythm/4o_audio_3.wav",
"output_path_miniomni": "/output/Mini-Omni/rhythm/mini-omni_03.wav",
"output_path_speechgpt": "/output/SpeechGPT/rhythm/SpeechGPT_answer_3.wav",
"output_path_funaudio": "/output/FunAudioLLM/rhythm/FunAudio_audio_3.1.wav",
"text_cn": "先按我的速度说出下面这句话，然后再慢慢地说一遍：“人工智能正在以多种方式改变世界。",
"language": "English",
"category": "Education",
"output_path_4o_cascade": "/output/cascade/rhythm/input_audio_3.wav",
"output_path_4o_llama_omni": "/output/LLaMA_omni/rhythm/input_audio_3.wav",
"level": "L3"
}
] |