Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- examples/AC/AudioCaps-Test/dataset_info.json +18 -0
- examples/AC/AudioCaps-Test/sample_0.wav +0 -0
- examples/AC/AudioCaps-Test/sample_1.wav +0 -0
- examples/AC/AudioCaps-Test/sample_2.wav +0 -0
- examples/AC/AudioCaps-Test/state.json +2 -1
- examples/AC/WavCaps-Test/dataset_info.json +18 -0
- examples/AC/WavCaps-Test/sample_0.wav +0 -0
- examples/AC/WavCaps-Test/sample_1.wav +0 -0
- examples/AC/WavCaps-Test/sample_2.wav +0 -0
- examples/AC/WavCaps-Test/state.json +2 -1
- examples/ASR/Common-Voice-15-En-Test/dataset_info.json +21 -3
- examples/ASR/Common-Voice-15-En-Test/sample_0.wav +0 -0
- examples/ASR/Common-Voice-15-En-Test/sample_1.wav +0 -0
- examples/ASR/Common-Voice-15-En-Test/sample_2.wav +0 -0
- examples/ASR/Common-Voice-15-En-Test/state.json +2 -1
- examples/ASR/Earnings21-Test/dataset_info.json +18 -0
- examples/ASR/Earnings21-Test/state.json +2 -1
- examples/ASR/Earnings22-Test/dataset_info.json +18 -0
- examples/ASR/Earnings22-Test/state.json +2 -1
- examples/ASR/GigaSpeech-Test/dataset_info.json +18 -0
- examples/ASR/GigaSpeech-Test/sample_0.wav +0 -0
- examples/ASR/GigaSpeech-Test/sample_1.wav +0 -0
- examples/ASR/GigaSpeech-Test/sample_2.wav +0 -0
- examples/ASR/GigaSpeech-Test/state.json +2 -1
- examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav +0 -0
- examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav +0 -0
- examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav +0 -0
- examples/ASR/IMDA-Part1-ASR-Test/state.json +1 -1
- examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav +0 -0
- examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav +0 -0
- examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav +0 -0
- examples/ASR/IMDA-Part2-ASR-Test/state.json +1 -1
- examples/ASR/LibriSpeech-Test-Clean/dataset_info.json +18 -0
- examples/ASR/LibriSpeech-Test-Clean/sample_0.wav +0 -0
- examples/ASR/LibriSpeech-Test-Clean/sample_1.wav +0 -0
- examples/ASR/LibriSpeech-Test-Clean/sample_2.wav +0 -0
- examples/ASR/LibriSpeech-Test-Clean/state.json +2 -1
- examples/ASR/LibriSpeech-Test-Other/dataset_info.json +18 -0
- examples/ASR/LibriSpeech-Test-Other/sample_0.wav +0 -0
- examples/ASR/LibriSpeech-Test-Other/sample_1.wav +0 -0
- examples/ASR/LibriSpeech-Test-Other/sample_2.wav +0 -0
- examples/ASR/LibriSpeech-Test-Other/state.json +2 -1
- examples/ASR/Peoples-Speech-Test/dataset_info.json +18 -0
- examples/ASR/Peoples-Speech-Test/sample_0.wav +0 -0
- examples/ASR/Peoples-Speech-Test/sample_1.wav +0 -0
- examples/ASR/Peoples-Speech-Test/sample_2.wav +0 -0
- examples/ASR/Peoples-Speech-Test/state.json +2 -1
- examples/ASR/Tedlium3-Longform-Test/dataset_info.json +18 -0
- examples/ASR/Tedlium3-Longform-Test/state.json +2 -1
.gitattributes
CHANGED
|
@@ -51,3 +51,4 @@ examples/SQA/SLUE-P2-SQA5-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
|
| 51 |
examples/SQA/Spoken-Squad-v1/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
| 52 |
examples/SQA/Spoken-Squad-v1/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
| 53 |
examples/SQA/Spoken-Squad-v1/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 51 |
examples/SQA/Spoken-Squad-v1/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
| 52 |
examples/SQA/Spoken-Squad-v1/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
| 53 |
examples/SQA/Spoken-Squad-v1/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
examples/SQA/DREAM-TTS-MCQ-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
examples/AC/AudioCaps-Test/dataset_info.json
CHANGED
|
@@ -118,6 +118,24 @@
|
|
| 118 |
"_type": "Value"
|
| 119 |
}
|
| 120 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
"qwen_audio_chat": {
|
| 122 |
"answer": {
|
| 123 |
"dtype": "string",
|
|
|
|
| 118 |
"_type": "Value"
|
| 119 |
}
|
| 120 |
},
|
| 121 |
+
"mowe_audio": {
|
| 122 |
+
"answer": {
|
| 123 |
+
"dtype": "string",
|
| 124 |
+
"_type": "Value"
|
| 125 |
+
},
|
| 126 |
+
"model_prediction": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
},
|
| 130 |
+
"task_type": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
},
|
| 134 |
+
"text": {
|
| 135 |
+
"dtype": "string",
|
| 136 |
+
"_type": "Value"
|
| 137 |
+
}
|
| 138 |
+
},
|
| 139 |
"qwen_audio_chat": {
|
| 140 |
"answer": {
|
| 141 |
"dtype": "string",
|
examples/AC/AudioCaps-Test/sample_0.wav
CHANGED
|
Binary files a/examples/AC/AudioCaps-Test/sample_0.wav and b/examples/AC/AudioCaps-Test/sample_0.wav differ
|
|
|
examples/AC/AudioCaps-Test/sample_1.wav
CHANGED
|
Binary files a/examples/AC/AudioCaps-Test/sample_1.wav and b/examples/AC/AudioCaps-Test/sample_1.wav differ
|
|
|
examples/AC/AudioCaps-Test/sample_2.wav
CHANGED
|
Binary files a/examples/AC/AudioCaps-Test/sample_2.wav and b/examples/AC/AudioCaps-Test/sample_2.wav differ
|
|
|
examples/AC/AudioCaps-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "e654a4081bc1365b",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/AC/WavCaps-Test/dataset_info.json
CHANGED
|
@@ -114,6 +114,24 @@
|
|
| 114 |
"_type": "Value"
|
| 115 |
}
|
| 116 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
"qwen_audio_chat": {
|
| 118 |
"answer": {
|
| 119 |
"dtype": "string",
|
|
|
|
| 114 |
"_type": "Value"
|
| 115 |
}
|
| 116 |
},
|
| 117 |
+
"mowe_audio": {
|
| 118 |
+
"answer": {
|
| 119 |
+
"dtype": "string",
|
| 120 |
+
"_type": "Value"
|
| 121 |
+
},
|
| 122 |
+
"model_prediction": {
|
| 123 |
+
"dtype": "string",
|
| 124 |
+
"_type": "Value"
|
| 125 |
+
},
|
| 126 |
+
"task_type": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
},
|
| 130 |
+
"text": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
"qwen_audio_chat": {
|
| 136 |
"answer": {
|
| 137 |
"dtype": "string",
|
examples/AC/WavCaps-Test/sample_0.wav
CHANGED
|
Binary files a/examples/AC/WavCaps-Test/sample_0.wav and b/examples/AC/WavCaps-Test/sample_0.wav differ
|
|
|
examples/AC/WavCaps-Test/sample_1.wav
CHANGED
|
Binary files a/examples/AC/WavCaps-Test/sample_1.wav and b/examples/AC/WavCaps-Test/sample_1.wav differ
|
|
|
examples/AC/WavCaps-Test/sample_2.wav
CHANGED
|
Binary files a/examples/AC/WavCaps-Test/sample_2.wav and b/examples/AC/WavCaps-Test/sample_2.wav differ
|
|
|
examples/AC/WavCaps-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "ce408e4cfa3eec8a",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/Common-Voice-15-En-Test/dataset_info.json
CHANGED
|
@@ -34,11 +34,11 @@
|
|
| 34 |
},
|
| 35 |
"other_attributes": {
|
| 36 |
"accents": {
|
| 37 |
-
"dtype": "
|
| 38 |
"_type": "Value"
|
| 39 |
},
|
| 40 |
"age": {
|
| 41 |
-
"dtype": "
|
| 42 |
"_type": "Value"
|
| 43 |
},
|
| 44 |
"client_id": {
|
|
@@ -50,7 +50,7 @@
|
|
| 50 |
"_type": "Value"
|
| 51 |
},
|
| 52 |
"gender": {
|
| 53 |
-
"dtype": "
|
| 54 |
"_type": "Value"
|
| 55 |
},
|
| 56 |
"language": {
|
|
@@ -146,6 +146,24 @@
|
|
| 146 |
"_type": "Value"
|
| 147 |
}
|
| 148 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
"qwen_audio_chat": {
|
| 150 |
"answer": {
|
| 151 |
"dtype": "string",
|
|
|
|
| 34 |
},
|
| 35 |
"other_attributes": {
|
| 36 |
"accents": {
|
| 37 |
+
"dtype": "string",
|
| 38 |
"_type": "Value"
|
| 39 |
},
|
| 40 |
"age": {
|
| 41 |
+
"dtype": "string",
|
| 42 |
"_type": "Value"
|
| 43 |
},
|
| 44 |
"client_id": {
|
|
|
|
| 50 |
"_type": "Value"
|
| 51 |
},
|
| 52 |
"gender": {
|
| 53 |
+
"dtype": "string",
|
| 54 |
"_type": "Value"
|
| 55 |
},
|
| 56 |
"language": {
|
|
|
|
| 146 |
"_type": "Value"
|
| 147 |
}
|
| 148 |
},
|
| 149 |
+
"mowe_audio": {
|
| 150 |
+
"answer": {
|
| 151 |
+
"dtype": "string",
|
| 152 |
+
"_type": "Value"
|
| 153 |
+
},
|
| 154 |
+
"model_prediction": {
|
| 155 |
+
"dtype": "string",
|
| 156 |
+
"_type": "Value"
|
| 157 |
+
},
|
| 158 |
+
"task_type": {
|
| 159 |
+
"dtype": "string",
|
| 160 |
+
"_type": "Value"
|
| 161 |
+
},
|
| 162 |
+
"text": {
|
| 163 |
+
"dtype": "string",
|
| 164 |
+
"_type": "Value"
|
| 165 |
+
}
|
| 166 |
+
},
|
| 167 |
"qwen_audio_chat": {
|
| 168 |
"answer": {
|
| 169 |
"dtype": "string",
|
examples/ASR/Common-Voice-15-En-Test/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/Common-Voice-15-En-Test/sample_0.wav and b/examples/ASR/Common-Voice-15-En-Test/sample_0.wav differ
|
|
|
examples/ASR/Common-Voice-15-En-Test/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/Common-Voice-15-En-Test/sample_1.wav and b/examples/ASR/Common-Voice-15-En-Test/sample_1.wav differ
|
|
|
examples/ASR/Common-Voice-15-En-Test/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/Common-Voice-15-En-Test/sample_2.wav and b/examples/ASR/Common-Voice-15-En-Test/sample_2.wav differ
|
|
|
examples/ASR/Common-Voice-15-En-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "6342d438049fbc7e",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/Earnings21-Test/dataset_info.json
CHANGED
|
@@ -110,6 +110,24 @@
|
|
| 110 |
"_type": "Value"
|
| 111 |
}
|
| 112 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
"qwen_audio_chat": {
|
| 114 |
"answer": {
|
| 115 |
"dtype": "string",
|
|
|
|
| 110 |
"_type": "Value"
|
| 111 |
}
|
| 112 |
},
|
| 113 |
+
"mowe_audio": {
|
| 114 |
+
"answer": {
|
| 115 |
+
"dtype": "string",
|
| 116 |
+
"_type": "Value"
|
| 117 |
+
},
|
| 118 |
+
"model_prediction": {
|
| 119 |
+
"dtype": "string",
|
| 120 |
+
"_type": "Value"
|
| 121 |
+
},
|
| 122 |
+
"task_type": {
|
| 123 |
+
"dtype": "string",
|
| 124 |
+
"_type": "Value"
|
| 125 |
+
},
|
| 126 |
+
"text": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
}
|
| 130 |
+
},
|
| 131 |
"qwen_audio_chat": {
|
| 132 |
"answer": {
|
| 133 |
"dtype": "string",
|
examples/ASR/Earnings21-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "d0ad1703cbc51418",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/Earnings22-Test/dataset_info.json
CHANGED
|
@@ -110,6 +110,24 @@
|
|
| 110 |
"_type": "Value"
|
| 111 |
}
|
| 112 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
"qwen_audio_chat": {
|
| 114 |
"answer": {
|
| 115 |
"dtype": "string",
|
|
|
|
| 110 |
"_type": "Value"
|
| 111 |
}
|
| 112 |
},
|
| 113 |
+
"mowe_audio": {
|
| 114 |
+
"answer": {
|
| 115 |
+
"dtype": "string",
|
| 116 |
+
"_type": "Value"
|
| 117 |
+
},
|
| 118 |
+
"model_prediction": {
|
| 119 |
+
"dtype": "string",
|
| 120 |
+
"_type": "Value"
|
| 121 |
+
},
|
| 122 |
+
"task_type": {
|
| 123 |
+
"dtype": "string",
|
| 124 |
+
"_type": "Value"
|
| 125 |
+
},
|
| 126 |
+
"text": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
}
|
| 130 |
+
},
|
| 131 |
"qwen_audio_chat": {
|
| 132 |
"answer": {
|
| 133 |
"dtype": "string",
|
examples/ASR/Earnings22-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "fb047ff90ed3a443",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/GigaSpeech-Test/dataset_info.json
CHANGED
|
@@ -138,6 +138,24 @@
|
|
| 138 |
"_type": "Value"
|
| 139 |
}
|
| 140 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
"qwen_audio_chat": {
|
| 142 |
"answer": {
|
| 143 |
"dtype": "string",
|
|
|
|
| 138 |
"_type": "Value"
|
| 139 |
}
|
| 140 |
},
|
| 141 |
+
"mowe_audio": {
|
| 142 |
+
"answer": {
|
| 143 |
+
"dtype": "string",
|
| 144 |
+
"_type": "Value"
|
| 145 |
+
},
|
| 146 |
+
"model_prediction": {
|
| 147 |
+
"dtype": "string",
|
| 148 |
+
"_type": "Value"
|
| 149 |
+
},
|
| 150 |
+
"task_type": {
|
| 151 |
+
"dtype": "string",
|
| 152 |
+
"_type": "Value"
|
| 153 |
+
},
|
| 154 |
+
"text": {
|
| 155 |
+
"dtype": "string",
|
| 156 |
+
"_type": "Value"
|
| 157 |
+
}
|
| 158 |
+
},
|
| 159 |
"qwen_audio_chat": {
|
| 160 |
"answer": {
|
| 161 |
"dtype": "string",
|
examples/ASR/GigaSpeech-Test/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/GigaSpeech-Test/sample_0.wav and b/examples/ASR/GigaSpeech-Test/sample_0.wav differ
|
|
|
examples/ASR/GigaSpeech-Test/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/GigaSpeech-Test/sample_1.wav and b/examples/ASR/GigaSpeech-Test/sample_1.wav differ
|
|
|
examples/ASR/GigaSpeech-Test/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/GigaSpeech-Test/sample_2.wav and b/examples/ASR/GigaSpeech-Test/sample_2.wav differ
|
|
|
examples/ASR/GigaSpeech-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "84a02614da440215",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav and b/examples/ASR/IMDA-Part1-ASR-Test/sample_0.wav differ
|
|
|
examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav and b/examples/ASR/IMDA-Part1-ASR-Test/sample_1.wav differ
|
|
|
examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav and b/examples/ASR/IMDA-Part1-ASR-Test/sample_2.wav differ
|
|
|
examples/ASR/IMDA-Part1-ASR-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "1514e693988caee7",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav and b/examples/ASR/IMDA-Part2-ASR-Test/sample_0.wav differ
|
|
|
examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav and b/examples/ASR/IMDA-Part2-ASR-Test/sample_1.wav differ
|
|
|
examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav and b/examples/ASR/IMDA-Part2-ASR-Test/sample_2.wav differ
|
|
|
examples/ASR/IMDA-Part2-ASR-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "8a8e117080f24a8b",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
examples/ASR/LibriSpeech-Test-Clean/dataset_info.json
CHANGED
|
@@ -122,6 +122,24 @@
|
|
| 122 |
"_type": "Value"
|
| 123 |
}
|
| 124 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
"qwen_audio_chat": {
|
| 126 |
"answer": {
|
| 127 |
"dtype": "string",
|
|
|
|
| 122 |
"_type": "Value"
|
| 123 |
}
|
| 124 |
},
|
| 125 |
+
"mowe_audio": {
|
| 126 |
+
"answer": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
},
|
| 130 |
+
"model_prediction": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
},
|
| 134 |
+
"task_type": {
|
| 135 |
+
"dtype": "string",
|
| 136 |
+
"_type": "Value"
|
| 137 |
+
},
|
| 138 |
+
"text": {
|
| 139 |
+
"dtype": "string",
|
| 140 |
+
"_type": "Value"
|
| 141 |
+
}
|
| 142 |
+
},
|
| 143 |
"qwen_audio_chat": {
|
| 144 |
"answer": {
|
| 145 |
"dtype": "string",
|
examples/ASR/LibriSpeech-Test-Clean/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/LibriSpeech-Test-Clean/sample_0.wav and b/examples/ASR/LibriSpeech-Test-Clean/sample_0.wav differ
|
|
|
examples/ASR/LibriSpeech-Test-Clean/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/LibriSpeech-Test-Clean/sample_1.wav and b/examples/ASR/LibriSpeech-Test-Clean/sample_1.wav differ
|
|
|
examples/ASR/LibriSpeech-Test-Clean/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/LibriSpeech-Test-Clean/sample_2.wav and b/examples/ASR/LibriSpeech-Test-Clean/sample_2.wav differ
|
|
|
examples/ASR/LibriSpeech-Test-Clean/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "cb0a09e53f0cc5db",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/LibriSpeech-Test-Other/dataset_info.json
CHANGED
|
@@ -122,6 +122,24 @@
|
|
| 122 |
"_type": "Value"
|
| 123 |
}
|
| 124 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
"qwen_audio_chat": {
|
| 126 |
"answer": {
|
| 127 |
"dtype": "string",
|
|
|
|
| 122 |
"_type": "Value"
|
| 123 |
}
|
| 124 |
},
|
| 125 |
+
"mowe_audio": {
|
| 126 |
+
"answer": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
},
|
| 130 |
+
"model_prediction": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
},
|
| 134 |
+
"task_type": {
|
| 135 |
+
"dtype": "string",
|
| 136 |
+
"_type": "Value"
|
| 137 |
+
},
|
| 138 |
+
"text": {
|
| 139 |
+
"dtype": "string",
|
| 140 |
+
"_type": "Value"
|
| 141 |
+
}
|
| 142 |
+
},
|
| 143 |
"qwen_audio_chat": {
|
| 144 |
"answer": {
|
| 145 |
"dtype": "string",
|
examples/ASR/LibriSpeech-Test-Other/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/LibriSpeech-Test-Other/sample_0.wav and b/examples/ASR/LibriSpeech-Test-Other/sample_0.wav differ
|
|
|
examples/ASR/LibriSpeech-Test-Other/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/LibriSpeech-Test-Other/sample_1.wav and b/examples/ASR/LibriSpeech-Test-Other/sample_1.wav differ
|
|
|
examples/ASR/LibriSpeech-Test-Other/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/LibriSpeech-Test-Other/sample_2.wav and b/examples/ASR/LibriSpeech-Test-Other/sample_2.wav differ
|
|
|
examples/ASR/LibriSpeech-Test-Other/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "0ed80d8ca27350ce",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/Peoples-Speech-Test/dataset_info.json
CHANGED
|
@@ -114,6 +114,24 @@
|
|
| 114 |
"_type": "Value"
|
| 115 |
}
|
| 116 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
"qwen_audio_chat": {
|
| 118 |
"answer": {
|
| 119 |
"dtype": "string",
|
|
|
|
| 114 |
"_type": "Value"
|
| 115 |
}
|
| 116 |
},
|
| 117 |
+
"mowe_audio": {
|
| 118 |
+
"answer": {
|
| 119 |
+
"dtype": "string",
|
| 120 |
+
"_type": "Value"
|
| 121 |
+
},
|
| 122 |
+
"model_prediction": {
|
| 123 |
+
"dtype": "string",
|
| 124 |
+
"_type": "Value"
|
| 125 |
+
},
|
| 126 |
+
"task_type": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
},
|
| 130 |
+
"text": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
"qwen_audio_chat": {
|
| 136 |
"answer": {
|
| 137 |
"dtype": "string",
|
examples/ASR/Peoples-Speech-Test/sample_0.wav
CHANGED
|
Binary files a/examples/ASR/Peoples-Speech-Test/sample_0.wav and b/examples/ASR/Peoples-Speech-Test/sample_0.wav differ
|
|
|
examples/ASR/Peoples-Speech-Test/sample_1.wav
CHANGED
|
Binary files a/examples/ASR/Peoples-Speech-Test/sample_1.wav and b/examples/ASR/Peoples-Speech-Test/sample_1.wav differ
|
|
|
examples/ASR/Peoples-Speech-Test/sample_2.wav
CHANGED
|
Binary files a/examples/ASR/Peoples-Speech-Test/sample_2.wav and b/examples/ASR/Peoples-Speech-Test/sample_2.wav differ
|
|
|
examples/ASR/Peoples-Speech-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "bf71989dac1baa0c",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|
examples/ASR/Tedlium3-Longform-Test/dataset_info.json
CHANGED
|
@@ -122,6 +122,24 @@
|
|
| 122 |
"_type": "Value"
|
| 123 |
}
|
| 124 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
"qwen_audio_chat": {
|
| 126 |
"answer": {
|
| 127 |
"dtype": "string",
|
|
|
|
| 122 |
"_type": "Value"
|
| 123 |
}
|
| 124 |
},
|
| 125 |
+
"mowe_audio": {
|
| 126 |
+
"answer": {
|
| 127 |
+
"dtype": "string",
|
| 128 |
+
"_type": "Value"
|
| 129 |
+
},
|
| 130 |
+
"model_prediction": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
},
|
| 134 |
+
"task_type": {
|
| 135 |
+
"dtype": "string",
|
| 136 |
+
"_type": "Value"
|
| 137 |
+
},
|
| 138 |
+
"text": {
|
| 139 |
+
"dtype": "string",
|
| 140 |
+
"_type": "Value"
|
| 141 |
+
}
|
| 142 |
+
},
|
| 143 |
"qwen_audio_chat": {
|
| 144 |
"answer": {
|
| 145 |
"dtype": "string",
|
examples/ASR/Tedlium3-Longform-Test/state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
|
|
|
| 17 |
"qwen_audio_chat"
|
| 18 |
],
|
| 19 |
"_format_kwargs": {},
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "16ff45685ee4694b",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
|
|
|
| 14 |
"wavllm_fairseq",
|
| 15 |
"Qwen2-Audio-7B-Instruct",
|
| 16 |
"whisper_large_v3_with_llama_3_8b_instruct",
|
| 17 |
+
"mowe_audio",
|
| 18 |
"qwen_audio_chat"
|
| 19 |
],
|
| 20 |
"_format_kwargs": {},
|