Hugging Face's logo

Spaces:
nvidia
/
audio-flamingo-3
Running on A100

App Files Community
1
audio-flamingo-3
File size: 3,177 Bytes 
174ae06
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
---
Clotho-AQA-AQA:
  _target_: llava.data.LLaVADataset
  data_path: Clotho-AQA-AQA/test.json
Music-AVQA-AQA_All:
  _target_: llava.data.LLaVADataset
  data_path: Music-AVQA-AQA_All/test.json
CochlScene-SceneClassification:
  _target_: llava.data.LLaVADataset
  data_path: CochlScene-SceneClassification/test.json
NSynth-Source:
  _target_: llava.data.LLaVADataset
  data_path: NSynth-Source/test.json
NSynth-Instrument:
  _target_: llava.data.LLaVADataset
  data_path: NSynth-Instrument/test.json
FSD50k-EventClassification:
  _target_: llava.data.LLaVADataset
  data_path: FSD50k-EventClassification/test.json
Clotho-v2-AudioCaptioning:
  _target_: llava.data.LLaVADataset
  data_path: Clotho-v2-AudioCaptioning/test.json
audiocaps-AudioCaptioning:
  _target_: llava.data.LLaVADataset
  data_path: audiocaps-AudioCaptioning/test.json
ravdess-EmotionClassification:
  _target_: llava.data.LLaVADataset
  data_path: ravdess-EmotionClassification/val.json
GTZAN-GenreClassification:
  _target_: llava.data.LLaVADataset
  data_path: GTZAN-GenreClassification/test.json
UrbanSound8K-EventClassification:
  _target_: llava.data.LLaVADataset
  data_path: UrbanSound8K-EventClassification/train.json
Medley-solos-DB-InstrClassification:
  _target_: llava.data.LLaVADataset
  data_path: Medley-solos-DB-InstrClassification/test.json
ESC50-EventClassification:
  _target_: llava.data.LLaVADataset
  data_path: ESC50-EventClassification/train.json
CREMA-D-EmotionClassification:
  _target_: llava.data.LLaVADataset
  data_path: CREMA-D-EmotionClassification/test.json
IEMOCAP-EmotionClassification:
  _target_: llava.data.LLaVADataset
  data_path: IEMOCAP-EmotionClassification/test.json
MELD-EmotionClassification:
  _target_: llava.data.LLaVADataset
  data_path: MELD-EmotionClassification/test.json
MELD-SentimentClassification:
  _target_: llava.data.LLaVADataset
  data_path: MELD-SentimentClassification/test.json
MMAU:
  _target_: llava.data.LLaVADataset
  data_path: MMAU/test.json
MMAU-mini:
  _target_: llava.data.LLaVADataset
  data_path: MMAU/test-mini.json
AudioEntailmentQA:
  _target_: llava.data.LLaVADataset
  data_path: AudioEntailmentQA/test.json
SPGI-ASR:
  _target_: llava.data.LLaVADataset
  data_path: SPGI-ASR/val.json
SWBD-ASR:
  _target_: llava.data.LLaVADataset
  data_path: SWBD-ASR/val.json
LibriSpeech-ASR-clean:
  _target_: llava.data.LLaVADataset
  data_path: LibriSpeech-ASR/test_clean.json
LibriSpeech-ASR-other:
  _target_: llava.data.LLaVADataset
  data_path: LibriSpeech-ASR/test_other.json
VoxPopuli-ASR:
  _target_: llava.data.LLaVADataset
  data_path: VoxPopuli-ASR/test.json
Europarl-ASR:
  _target_: llava.data.LLaVADataset
  data_path: Europarl-ASR/test.json
CV-ASR:
  _target_: llava.data.LLaVADataset
  data_path: CV-ASR/test.json
GigaSpeech-ASR:
  _target_: llava.data.LLaVADataset
  data_path: GigaSpeech-ASR/test.json
CompA-R-AQA:
  _target_: llava.data.LLaVADataset
  data_path: CompA-R-AQA/test.json
MuschoMusicQA:
  _target_: llava.data.LLaVADataset
  data_path: MuschoMusicQA/test.json
CMM:
  _target_: llava.data.LLaVADataset
  data_path: CMM/test.json
AIR-Bench:
  _target_: llava.data.LLaVADataset
  data_path: AIR-Bench/test.json