Upload folder using huggingface_hub
Browse files- config.json +27 -0
- merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- preprocessor_config.json +22 -0
- quantize_config.json +50 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "laion/clap-htsat-unfused",
|
3 |
+
"architectures": [
|
4 |
+
"ClapModel"
|
5 |
+
],
|
6 |
+
"audio_config": {
|
7 |
+
"fusion_num_hidden_layers": 2,
|
8 |
+
"model_type": "clap_audio_model",
|
9 |
+
"projection_hidden_size": 768
|
10 |
+
},
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"logit_scale_init_value": 14.285714285714285,
|
14 |
+
"model_type": "clap",
|
15 |
+
"num_hidden_layers": 16,
|
16 |
+
"projection_dim": 512,
|
17 |
+
"projection_hidden_act": "relu",
|
18 |
+
"text_config": {
|
19 |
+
"classifier_dropout": null,
|
20 |
+
"fusion_hidden_size": 768,
|
21 |
+
"fusion_num_hidden_layers": 2,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"model_type": "clap_text_model",
|
24 |
+
"projection_hidden_size": 768
|
25 |
+
},
|
26 |
+
"transformers_version": "4.36.0.dev0"
|
27 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8cbfb96dda10259964e678c1557466f925001f66b8cd1b24c84bd88b0f84345
|
3 |
+
size 619128635
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f559313ec268518193101007fc0569ee4b2cfac03e369091c50adb4795f5c5d
|
3 |
+
size 161024085
|
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 |
+
}
|
quantize_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Expand",
|
8 |
+
"ScatterND",
|
9 |
+
"Pad",
|
10 |
+
"Abs",
|
11 |
+
"Unsqueeze",
|
12 |
+
"ReduceSum",
|
13 |
+
"Not",
|
14 |
+
"CumSum",
|
15 |
+
"Constant",
|
16 |
+
"Exp",
|
17 |
+
"Sub",
|
18 |
+
"MatMul",
|
19 |
+
"Cast",
|
20 |
+
"Reshape",
|
21 |
+
"Flatten",
|
22 |
+
"Resize",
|
23 |
+
"Conv",
|
24 |
+
"ConstantOfShape",
|
25 |
+
"Gather",
|
26 |
+
"Relu",
|
27 |
+
"Div",
|
28 |
+
"Mul",
|
29 |
+
"GlobalAveragePool",
|
30 |
+
"Range",
|
31 |
+
"Erf",
|
32 |
+
"Where",
|
33 |
+
"ReduceMean",
|
34 |
+
"Pow",
|
35 |
+
"Shape",
|
36 |
+
"Concat",
|
37 |
+
"Slice",
|
38 |
+
"Softmax",
|
39 |
+
"Tanh",
|
40 |
+
"Sqrt",
|
41 |
+
"BatchNormalization",
|
42 |
+
"Add",
|
43 |
+
"Transpose",
|
44 |
+
"Gemm",
|
45 |
+
"Equal"
|
46 |
+
],
|
47 |
+
"weight_type": "QUInt8"
|
48 |
+
}
|
49 |
+
}
|
50 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
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": 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 |
+
"trust_remote_code": false,
|
62 |
+
"unk_token": "<unk>"
|
63 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|