Upload folder using huggingface_hub

.gitattributes

@@ -60,3 +60,21 @@ examples/SQA/CN-College-Listen-MCQ-Test/sample_0.wav filter=lfs diff=lfs merge=l
 examples/SQA/Spoken-Squad-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
 examples/SQA/Spoken-Squad-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
 examples/SQA/Spoken-Squad-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Earnings21-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Earnings21-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Earnings21-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Earnings22-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Earnings22-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Earnings22-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Tedlium3-Long-form-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Tedlium3-Long-form-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
+examples/2ASR/Tedlium3-Long-form-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/CN-College-Listen-MCQ-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/Public-SG-Speech-QA-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/SLUE-P2-SQA5-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/SLUE-P2-SQA5-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/SLUE-P2-SQA5-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/Spoken-Squad-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/Spoken-Squad-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
+examples/2SQA/Spoken-Squad-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
+examples/SQA/DREAM-TTS-MCQ-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text

examples/2AC/AudioCaps-Test/dataset_info.json

@@ -0,0 +1,160 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "audiocap_id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "start_time": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "youtube_id": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2AC/AudioCaps-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "e736bf1821a473f3",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2AC/WavCaps-Test/dataset_info.json

@@ -0,0 +1,156 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "audio_path": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "duration": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2AC/WavCaps-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "742ab313af054565",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2AQA/AudioCaps-QA-Test/dataset_info.json

@@ -0,0 +1,164 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "audiocap_id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "caption": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "start_time": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "youtube_id": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2AQA/AudioCaps-QA-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "52bc1dfcaf2a0f4b",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2AQA/Clotho-AQA-Test/dataset_info.json

@@ -0,0 +1,147 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {},
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2AQA/Clotho-AQA-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "e2e76326f448d7c4",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2AQA/WavCaps-QA-Test/dataset_info.json

@@ -0,0 +1,160 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "audio_path": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "caption": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "duration": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2AQA/WavCaps-QA-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "40995a6cc1fe3dc7",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2AR/VoxCeleb-Accent-Test/dataset_info.json

@@ -0,0 +1,168 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "Gender": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "Nationality": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "VGGFace1 ID": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "VoxCeleb1 ID": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "index": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2AR/VoxCeleb-Accent-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "fa91a59f90c22c3c",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2ASR/Common-Voice-15-En-Test/dataset_info.json

@@ -0,0 +1,188 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "accents": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "age": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "client_id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "down_votes": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "gender": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "language": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "locale": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "segment": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "up_votes": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "variant": {
+        "dtype": "null",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2ASR/Common-Voice-15-En-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "468db91ad949e4d4",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2ASR/Earnings21-Test/dataset_info.json

@@ -0,0 +1,152 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "id": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2ASR/Earnings21-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "8cc0ad99446f1aba",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2ASR/Earnings22-Test/dataset_info.json

@@ -0,0 +1,152 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "id": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2ASR/Earnings22-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "331c061bce6e651c",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2ASR/GigaSpeech-Test2/dataset_info.json

@@ -0,0 +1,180 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "audio_id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "begin_time": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "category": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "end_time": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "segment_id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "source": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "speaker": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "url": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "mowe_audio": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2ASR/GigaSpeech-Test2/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "68d371cc267ff1d2",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "mowe_audio",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

examples/2ASR/IMDA-Part1-ASR-Test/dataset_info.json

@@ -0,0 +1,200 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "context": {
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "audio": {
+        "sampling_rate": 16000,
+        "_type": "Audio"
+      }
+    },
+    "instruction": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "answer": {
+      "audio": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "other_attributes": {
+      "conversation_id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "partition": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "settings": {
+        "channel": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "session": {
+          "dtype": "string",
+          "_type": "Value"
+        }
+      },
+      "speaker": {
+        "device_c0": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "device_c1": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "device_c2": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "ethnic_group": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "gender": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "part1_id": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "part2_id": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "speaker_id": {
+          "dtype": "string",
+          "_type": "Value"
+        }
+      }
+    },
+    "salmonn_7b": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "wavllm_fairseq": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Qwen2-Audio-7B-Instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "meralion_audiollm_v1_lora": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "whisper_large_v3_with_llama_3_8b_instruct": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "qwen_audio_chat": {
+      "answer": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "model_prediction": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "text": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

examples/2ASR/IMDA-Part1-ASR-Test/state.json

@@ -0,0 +1,24 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "ddfb47abed13c356",
+  "_format_columns": [
+    "context",
+    "instruction",
+    "answer",
+    "other_attributes",
+    "salmonn_7b",
+    "wavllm_fairseq",
+    "Qwen2-Audio-7B-Instruct",
+    "meralion_audiollm_v1_lora",
+    "whisper_large_v3_with_llama_3_8b_instruct",
+    "qwen_audio_chat"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}