Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +4 -0
- examples/AC/AudioCaps-Test/data-00000-of-00001.arrow +2 -2
- 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 +1 -1
- examples/AC/WavCaps-Test/data-00000-of-00001.arrow +2 -2
- 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 +1 -1
- examples/AQA/AudioCaps-QA-Test/data-00000-of-00001.arrow +2 -2
- examples/AQA/AudioCaps-QA-Test/dataset_info.json +18 -0
- examples/AQA/AudioCaps-QA-Test/sample_0.wav +0 -0
- examples/AQA/AudioCaps-QA-Test/sample_1.wav +0 -0
- examples/AQA/AudioCaps-QA-Test/sample_2.wav +0 -0
- examples/AQA/AudioCaps-QA-Test/state.json +2 -1
- examples/AQA/Clotho-AQA-Test/data-00000-of-00001.arrow +2 -2
- examples/AQA/Clotho-AQA-Test/dataset_info.json +1 -91
- examples/AQA/Clotho-AQA-Test/sample_0.wav +0 -0
- examples/AQA/Clotho-AQA-Test/sample_1.wav +0 -0
- examples/AQA/Clotho-AQA-Test/sample_2.wav +0 -0
- examples/AQA/Clotho-AQA-Test/state.json +2 -7
- examples/AQA/WavCaps-QA-Test/data-00000-of-00001.arrow +2 -2
- examples/AQA/WavCaps-QA-Test/dataset_info.json +18 -0
- examples/AQA/WavCaps-QA-Test/sample_0.wav +0 -0
- examples/AQA/WavCaps-QA-Test/sample_1.wav +0 -0
- examples/AQA/WavCaps-QA-Test/sample_2.wav +0 -0
- examples/AQA/WavCaps-QA-Test/state.json +2 -1
- examples/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow +2 -2
- examples/AR/VoxCeleb-Accent-Test/dataset_info.json +18 -0
- examples/AR/VoxCeleb-Accent-Test/sample_0.wav +0 -0
- examples/AR/VoxCeleb-Accent-Test/sample_1.wav +0 -0
- examples/AR/VoxCeleb-Accent-Test/sample_2.wav +0 -0
- examples/AR/VoxCeleb-Accent-Test/state.json +2 -1
- examples/ASR/Common-Voice-15-En-Test/data-00000-of-00001.arrow +2 -2
- examples/ASR/Common-Voice-15-En-Test/dataset_info.json +3 -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 +1 -1
- examples/ASR/Earnings21-Test/data-00000-of-00001.arrow +2 -2
- examples/ASR/Earnings21-Test/sample_0.wav +2 -2
- examples/ASR/Earnings21-Test/sample_1.wav +2 -2
- examples/ASR/Earnings21-Test/sample_2.wav +2 -2
- examples/ASR/Earnings21-Test/state.json +1 -1
- examples/ASR/Earnings22-Test/data-00000-of-00001.arrow +2 -2
- examples/ASR/Earnings22-Test/sample_0.wav +2 -2
- examples/ASR/Earnings22-Test/sample_1.wav +2 -2
- examples/ASR/Earnings22-Test/sample_2.wav +2 -2
.gitattributes
CHANGED
|
@@ -52,3 +52,7 @@ 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 55 |
+
examples/ASR/Tedlium3-Long-form-Test/sample_0.wav filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
examples/ASR/Tedlium3-Long-form-Test/sample_1.wav filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
examples/ASR/Tedlium3-Long-form-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
examples/SQA/Public-SG-Speech-QA-Test/sample_2.wav filter=lfs diff=lfs merge=lfs -text
|
examples/AC/AudioCaps-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b86af8e9fe94528cc1e80ab8e1543dcccb04421c9e73d50a03bec19bd5b22f8
|
| 3 |
+
size 972360
|
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",
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "3729f6c56764c342",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
examples/AC/WavCaps-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:398df95837d355a7b2329ce2e6805f8a6b88867630bf6650c1f04ca71c9819b9
|
| 3 |
+
size 720624
|
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",
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "6c3c2a5f2db349d8",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
examples/AQA/AudioCaps-QA-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:545f230fd01be33ef8447cf2acacc791d2be64b72311230ee3660dcfc282c609
|
| 3 |
+
size 971952
|
examples/AQA/AudioCaps-QA-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/AQA/AudioCaps-QA-Test/sample_0.wav
CHANGED
|
Binary files a/examples/AQA/AudioCaps-QA-Test/sample_0.wav and b/examples/AQA/AudioCaps-QA-Test/sample_0.wav differ
|
|
|
examples/AQA/AudioCaps-QA-Test/sample_1.wav
CHANGED
|
Binary files a/examples/AQA/AudioCaps-QA-Test/sample_1.wav and b/examples/AQA/AudioCaps-QA-Test/sample_1.wav differ
|
|
|
examples/AQA/AudioCaps-QA-Test/sample_2.wav
CHANGED
|
Binary files a/examples/AQA/AudioCaps-QA-Test/sample_2.wav and b/examples/AQA/AudioCaps-QA-Test/sample_2.wav differ
|
|
|
examples/AQA/AudioCaps-QA-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": "026dfac674d9ef77",
|
| 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/AQA/Clotho-AQA-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c706ed113af21d49025bd52ba2ebb8fce382ef5c4ecfac32b6173222ae4953b0
|
| 3 |
+
size 1907768
|
examples/AQA/Clotho-AQA-Test/dataset_info.json
CHANGED
|
@@ -32,97 +32,7 @@
|
|
| 32 |
"_type": "Value"
|
| 33 |
}
|
| 34 |
},
|
| 35 |
-
"other_attributes": {}
|
| 36 |
-
"salmonn_7b": {
|
| 37 |
-
"answer": {
|
| 38 |
-
"dtype": "string",
|
| 39 |
-
"_type": "Value"
|
| 40 |
-
},
|
| 41 |
-
"model_prediction": {
|
| 42 |
-
"dtype": "string",
|
| 43 |
-
"_type": "Value"
|
| 44 |
-
},
|
| 45 |
-
"task_type": {
|
| 46 |
-
"dtype": "string",
|
| 47 |
-
"_type": "Value"
|
| 48 |
-
},
|
| 49 |
-
"text": {
|
| 50 |
-
"dtype": "string",
|
| 51 |
-
"_type": "Value"
|
| 52 |
-
}
|
| 53 |
-
},
|
| 54 |
-
"wavllm_fairseq": {
|
| 55 |
-
"answer": {
|
| 56 |
-
"dtype": "string",
|
| 57 |
-
"_type": "Value"
|
| 58 |
-
},
|
| 59 |
-
"model_prediction": {
|
| 60 |
-
"dtype": "string",
|
| 61 |
-
"_type": "Value"
|
| 62 |
-
},
|
| 63 |
-
"task_type": {
|
| 64 |
-
"dtype": "string",
|
| 65 |
-
"_type": "Value"
|
| 66 |
-
},
|
| 67 |
-
"text": {
|
| 68 |
-
"dtype": "string",
|
| 69 |
-
"_type": "Value"
|
| 70 |
-
}
|
| 71 |
-
},
|
| 72 |
-
"Qwen2-Audio-7B-Instruct": {
|
| 73 |
-
"answer": {
|
| 74 |
-
"dtype": "string",
|
| 75 |
-
"_type": "Value"
|
| 76 |
-
},
|
| 77 |
-
"model_prediction": {
|
| 78 |
-
"dtype": "string",
|
| 79 |
-
"_type": "Value"
|
| 80 |
-
},
|
| 81 |
-
"task_type": {
|
| 82 |
-
"dtype": "string",
|
| 83 |
-
"_type": "Value"
|
| 84 |
-
},
|
| 85 |
-
"text": {
|
| 86 |
-
"dtype": "string",
|
| 87 |
-
"_type": "Value"
|
| 88 |
-
}
|
| 89 |
-
},
|
| 90 |
-
"whisper_large_v3_with_llama_3_8b_instruct": {
|
| 91 |
-
"answer": {
|
| 92 |
-
"dtype": "string",
|
| 93 |
-
"_type": "Value"
|
| 94 |
-
},
|
| 95 |
-
"model_prediction": {
|
| 96 |
-
"dtype": "string",
|
| 97 |
-
"_type": "Value"
|
| 98 |
-
},
|
| 99 |
-
"task_type": {
|
| 100 |
-
"dtype": "string",
|
| 101 |
-
"_type": "Value"
|
| 102 |
-
},
|
| 103 |
-
"text": {
|
| 104 |
-
"dtype": "string",
|
| 105 |
-
"_type": "Value"
|
| 106 |
-
}
|
| 107 |
-
},
|
| 108 |
-
"qwen_audio_chat": {
|
| 109 |
-
"answer": {
|
| 110 |
-
"dtype": "string",
|
| 111 |
-
"_type": "Value"
|
| 112 |
-
},
|
| 113 |
-
"model_prediction": {
|
| 114 |
-
"dtype": "string",
|
| 115 |
-
"_type": "Value"
|
| 116 |
-
},
|
| 117 |
-
"task_type": {
|
| 118 |
-
"dtype": "string",
|
| 119 |
-
"_type": "Value"
|
| 120 |
-
},
|
| 121 |
-
"text": {
|
| 122 |
-
"dtype": "string",
|
| 123 |
-
"_type": "Value"
|
| 124 |
-
}
|
| 125 |
-
}
|
| 126 |
},
|
| 127 |
"homepage": "",
|
| 128 |
"license": ""
|
|
|
|
| 32 |
"_type": "Value"
|
| 33 |
}
|
| 34 |
},
|
| 35 |
+
"other_attributes": {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
},
|
| 37 |
"homepage": "",
|
| 38 |
"license": ""
|
examples/AQA/Clotho-AQA-Test/sample_0.wav
CHANGED
|
Binary files a/examples/AQA/Clotho-AQA-Test/sample_0.wav and b/examples/AQA/Clotho-AQA-Test/sample_0.wav differ
|
|
|
examples/AQA/Clotho-AQA-Test/sample_1.wav
CHANGED
|
Binary files a/examples/AQA/Clotho-AQA-Test/sample_1.wav and b/examples/AQA/Clotho-AQA-Test/sample_1.wav differ
|
|
|
examples/AQA/Clotho-AQA-Test/sample_2.wav
CHANGED
|
Binary files a/examples/AQA/Clotho-AQA-Test/sample_2.wav and b/examples/AQA/Clotho-AQA-Test/sample_2.wav differ
|
|
|
examples/AQA/Clotho-AQA-Test/state.json
CHANGED
|
@@ -4,17 +4,12 @@
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
-
"_fingerprint": "
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
| 11 |
"answer",
|
| 12 |
-
"other_attributes"
|
| 13 |
-
"salmonn_7b",
|
| 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": {},
|
| 20 |
"_format_type": null,
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "515a1722077187bd",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
| 11 |
"answer",
|
| 12 |
+
"other_attributes"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
],
|
| 14 |
"_format_kwargs": {},
|
| 15 |
"_format_type": null,
|
examples/AQA/WavCaps-QA-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c33abcdce0b35d086c28cf0ba814d9edabfb596c0f40b312968d2e32d30f4432
|
| 3 |
+
size 976888
|
examples/AQA/WavCaps-QA-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/AQA/WavCaps-QA-Test/sample_0.wav
CHANGED
|
Binary files a/examples/AQA/WavCaps-QA-Test/sample_0.wav and b/examples/AQA/WavCaps-QA-Test/sample_0.wav differ
|
|
|
examples/AQA/WavCaps-QA-Test/sample_1.wav
CHANGED
|
Binary files a/examples/AQA/WavCaps-QA-Test/sample_1.wav and b/examples/AQA/WavCaps-QA-Test/sample_1.wav differ
|
|
|
examples/AQA/WavCaps-QA-Test/sample_2.wav
CHANGED
|
Binary files a/examples/AQA/WavCaps-QA-Test/sample_2.wav and b/examples/AQA/WavCaps-QA-Test/sample_2.wav differ
|
|
|
examples/AQA/WavCaps-QA-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": "46b38bc22103a7cd",
|
| 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/AR/VoxCeleb-Accent-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f899c6ad68e95ddacddf1c017f802018d1089d084831b573f5fb81431b0b98a9
|
| 3 |
+
size 1145784
|
examples/AR/VoxCeleb-Accent-Test/dataset_info.json
CHANGED
|
@@ -126,6 +126,24 @@
|
|
| 126 |
"_type": "Value"
|
| 127 |
}
|
| 128 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
"qwen_audio_chat": {
|
| 130 |
"answer": {
|
| 131 |
"dtype": "string",
|
|
|
|
| 126 |
"_type": "Value"
|
| 127 |
}
|
| 128 |
},
|
| 129 |
+
"mowe_audio": {
|
| 130 |
+
"answer": {
|
| 131 |
+
"dtype": "string",
|
| 132 |
+
"_type": "Value"
|
| 133 |
+
},
|
| 134 |
+
"model_prediction": {
|
| 135 |
+
"dtype": "string",
|
| 136 |
+
"_type": "Value"
|
| 137 |
+
},
|
| 138 |
+
"task_type": {
|
| 139 |
+
"dtype": "string",
|
| 140 |
+
"_type": "Value"
|
| 141 |
+
},
|
| 142 |
+
"text": {
|
| 143 |
+
"dtype": "string",
|
| 144 |
+
"_type": "Value"
|
| 145 |
+
}
|
| 146 |
+
},
|
| 147 |
"qwen_audio_chat": {
|
| 148 |
"answer": {
|
| 149 |
"dtype": "string",
|
examples/AR/VoxCeleb-Accent-Test/sample_0.wav
CHANGED
|
Binary files a/examples/AR/VoxCeleb-Accent-Test/sample_0.wav and b/examples/AR/VoxCeleb-Accent-Test/sample_0.wav differ
|
|
|
examples/AR/VoxCeleb-Accent-Test/sample_1.wav
CHANGED
|
Binary files a/examples/AR/VoxCeleb-Accent-Test/sample_1.wav and b/examples/AR/VoxCeleb-Accent-Test/sample_1.wav differ
|
|
|
examples/AR/VoxCeleb-Accent-Test/sample_2.wav
CHANGED
|
Binary files a/examples/AR/VoxCeleb-Accent-Test/sample_2.wav and b/examples/AR/VoxCeleb-Accent-Test/sample_2.wav differ
|
|
|
examples/AR/VoxCeleb-Accent-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": "f1df87f5b3ca8c97",
|
| 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/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d297ee75cd36249355aec83e6526d78c2592e44b1ca8865a31e3df576a0002dc
|
| 3 |
+
size 817384
|
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": {
|
|
|
|
| 34 |
},
|
| 35 |
"other_attributes": {
|
| 36 |
"accents": {
|
| 37 |
+
"dtype": "null",
|
| 38 |
"_type": "Value"
|
| 39 |
},
|
| 40 |
"age": {
|
| 41 |
+
"dtype": "null",
|
| 42 |
"_type": "Value"
|
| 43 |
},
|
| 44 |
"client_id": {
|
|
|
|
| 50 |
"_type": "Value"
|
| 51 |
},
|
| 52 |
"gender": {
|
| 53 |
+
"dtype": "null",
|
| 54 |
"_type": "Value"
|
| 55 |
},
|
| 56 |
"language": {
|
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",
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "5a02a12eee6eb15a",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
examples/ASR/Earnings21-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bada2056866d5e784c649b65add3928a859b35304e9e240e59f94da9f60ccaf
|
| 3 |
+
size 235999160
|
examples/ASR/Earnings21-Test/sample_0.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db092ee918b48e37b79b079e2de667d127c0008293a0309be1c6a16a4840b820
|
| 3 |
+
size 46016300
|
examples/ASR/Earnings21-Test/sample_1.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64031076b7b5a039154ac523bf5a7938d4b1dd8bb30a9a9f55c4cf579347a75a
|
| 3 |
+
size 80607654
|
examples/ASR/Earnings21-Test/sample_2.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33430292a1535095ad33c1b6e428d77d0bdba85a0299eee6a36f45e100c39392
|
| 3 |
+
size 108053804
|
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",
|
|
|
|
| 4 |
"filename": "data-00000-of-00001.arrow"
|
| 5 |
}
|
| 6 |
],
|
| 7 |
+
"_fingerprint": "0d42a0f2cebd16d8",
|
| 8 |
"_format_columns": [
|
| 9 |
"context",
|
| 10 |
"instruction",
|
examples/ASR/Earnings22-Test/data-00000-of-00001.arrow
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12c1522382953c79af65ca9df82606ab5aef8aea8c9646e4ecd3de94fc9d8d62
|
| 3 |
+
size 220986632
|
examples/ASR/Earnings22-Test/sample_0.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:148fc052e32561e0b60d3e3c86b4fd4c2b319ff9aefd1b2b718cf12e2a2a457c
|
| 3 |
+
size 64738578
|
examples/ASR/Earnings22-Test/sample_1.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3ed5fea7d5d300ae1dabe9391dddee347c54c82fa4356bc12e9ba5a28238edc
|
| 3 |
+
size 101514284
|
examples/ASR/Earnings22-Test/sample_2.wav
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec1e241971074b8965b7069596c5fa1c7cf42573e3a341eec76857239088a0a5
|
| 3 |
+
size 53823852
|