Hugging Face's logo

vinhbui
/
clap-test

Safetensors
clap_audio_model
Model card Files
xet
Community
vinhbui commited on
Commit
bb8c22b
·
verified ·
1 Parent(s): 8ca3cce

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +49 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +22 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +62 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "laion/larger_clap_general",
3
+ "aff_block_r": 4,
4
+ "architectures": [
5
+ "ClapAudioModel"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "depths": [
9
+ 2,
10
+ 2,
11
+ 12,
12
+ 2
13
+ ],
14
+ "drop_path_rate": 0.0,
15
+ "enable_fusion": false,
16
+ "enable_patch_layer_norm": true,
17
+ "flatten_patch_embeds": true,
18
+ "fusion_type": null,
19
+ "hidden_act": "gelu",
20
+ "hidden_dropout_prob": 0.1,
21
+ "hidden_size": 1024,
22
+ "initializer_factor": 1.0,
23
+ "layer_norm_eps": 1e-05,
24
+ "mlp_ratio": 4.0,
25
+ "model_type": "clap_audio_model",
26
+ "num_attention_heads": [
27
+ 4,
28
+ 8,
29
+ 16,
30
+ 32
31
+ ],
32
+ "num_classes": 527,
33
+ "num_hidden_layers": 4,
34
+ "num_mel_bins": 64,
35
+ "patch_embed_input_channels": 1,
36
+ "patch_embeds_hidden_size": 128,
37
+ "patch_size": 4,
38
+ "patch_stride": [
39
+ 4,
40
+ 4
41
+ ],
42
+ "projection_dim": 512,
43
+ "projection_hidden_act": "relu",
44
+ "qkv_bias": true,
45
+ "spec_size": 256,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.46.3",
48
+ "window_size": 8
49
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c346f3ba8b9e2549d52d69193745d588b5513b2d8a2a71cfcd90f484625c6f
3
+ size 271931456
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": 10,
3
+ "feature_extractor_type": "ClapFeatureExtractor",
4
+ "feature_size": 64,
5
+ "fft_window_size": 1024,
6
+ "frequency_max": 14000,
7
+ "frequency_min": 50,
8
+ "hop_length": 480,
9
+ "max_length_s": 10,
10
+ "n_fft": 1024,
11
+ "nb_frequency_bins": 513,
12
+ "nb_max_frames": 1000,
13
+ "nb_max_samples": 480000,
14
+ "padding": "repeatpad",
15
+ "padding_side": "right",
16
+ "padding_value": 0.0,
17
+ "processor_class": "ClapProcessor",
18
+ "return_attention_mask": false,
19
+ "sampling_rate": 48000,
20
+ "top_db": null,
21
+ "truncation": "rand_trunc"
22
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": null,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "processor_class": "ClapProcessor",
58
+ "sep_token": "</s>",
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "unk_token": "<unk>"
62
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff