Hugging Face's logo

sarulab-speech
/
human-clap-mae

Safetensors
clap
Model card Files Community
ttakano398 commited on
Commit
adbdfb6
·
verified ·
1 Parent(s): b269ebe

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +88 -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 +63 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ClapModel"
4
+ ],
5
+ "audio_config": {
6
+ "_attn_implementation_autoset": true,
7
+ "aff_block_r": 4,
8
+ "attention_probs_dropout_prob": 0.0,
9
+ "depths": [
10
+ 2,
11
+ 2,
12
+ 6,
13
+ 2
14
+ ],
15
+ "drop_path_rate": 0.0,
16
+ "enable_fusion": true,
17
+ "enable_patch_fusion": true,
18
+ "enable_patch_layer_norm": true,
19
+ "flatten_patch_embeds": true,
20
+ "fusion_num_hidden_layers": 2,
21
+ "fusion_type": null,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.1,
24
+ "hidden_size": 768,
25
+ "initializer_factor": 1.0,
26
+ "layer_norm_eps": 1e-05,
27
+ "mlp_ratio": 4.0,
28
+ "model_type": "clap_audio_model",
29
+ "num_attention_heads": [
30
+ 4,
31
+ 8,
32
+ 16,
33
+ 32
34
+ ],
35
+ "num_classes": 527,
36
+ "num_hidden_layers": 4,
37
+ "num_mel_bins": 64,
38
+ "patch_embed_input_channels": 1,
39
+ "patch_embeds_hidden_size": 96,
40
+ "patch_size": 4,
41
+ "patch_stride": [
42
+ 4,
43
+ 4
44
+ ],
45
+ "projection_dim": 512,
46
+ "projection_hidden_act": "relu",
47
+ "projection_hidden_size": 768,
48
+ "qkv_bias": true,
49
+ "spec_size": 256,
50
+ "torch_dtype": "float32",
51
+ "window_size": 8
52
+ },
53
+ "hidden_size": 768,
54
+ "initializer_factor": 1.0,
55
+ "logit_scale_init_value": 14.285714285714285,
56
+ "model_type": "clap",
57
+ "num_hidden_layers": 16,
58
+ "projection_dim": 512,
59
+ "projection_hidden_act": "relu",
60
+ "text_config": {
61
+ "_attn_implementation_autoset": true,
62
+ "attention_probs_dropout_prob": 0.1,
63
+ "classifier_dropout": null,
64
+ "fusion_hidden_size": 768,
65
+ "fusion_num_hidden_layers": 2,
66
+ "hidden_act": "gelu",
67
+ "hidden_dropout_prob": 0.1,
68
+ "hidden_size": 768,
69
+ "initializer_factor": 1.0,
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 3072,
72
+ "layer_norm_eps": 1e-12,
73
+ "max_position_embeddings": 514,
74
+ "model_type": "clap_text_model",
75
+ "num_attention_heads": 12,
76
+ "num_hidden_layers": 12,
77
+ "position_embedding_type": "absolute",
78
+ "projection_dim": 512,
79
+ "projection_hidden_act": "relu",
80
+ "projection_hidden_size": 768,
81
+ "torch_dtype": "float32",
82
+ "type_vocab_size": 1,
83
+ "use_cache": true,
84
+ "vocab_size": 50265
85
+ },
86
+ "torch_dtype": "float32",
87
+ "transformers_version": "4.50.0"
88
+ }
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 sha256:322f3c29e210aee7c864228614b629af1a14b01fca5541ecb6ce7a5bb49f0a5b
3
+ size 614496152
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": "fusion"
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "max_length": null,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "processor_class": "ClapProcessor",
59
+ "sep_token": "</s>",
60
+ "tokenizer_class": "RobertaTokenizer",
61
+ "trim_offsets": true,
62
+ "unk_token": "<unk>"
63
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff