Hugging Face's logo

YU310takuto
/
clap_emospeechtest_ver0.1

Safetensors
Model card Files Community
YU310takuto commited on
Commit
7a68968
·
verified ·
1 Parent(s): 015080b

Upload 21 files

Browse files
Files changed (21) hide show
  1. clap_finetuned/.ipynb_checkpoints/config-checkpoint.json +29 -0
  2. clap_finetuned/.ipynb_checkpoints/merges-checkpoint.txt +0 -0
  3. clap_finetuned/.ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
  4. clap_finetuned/.ipynb_checkpoints/tokenizer_config-checkpoint.json +62 -0
  5. clap_finetuned/.ipynb_checkpoints/vocab-checkpoint.json +0 -0
  6. clap_finetuned/checkpoint-50/.ipynb_checkpoints/trainer_state-checkpoint.json +61 -0
  7. clap_finetuned/checkpoint-50/config.json +29 -0
  8. clap_finetuned/checkpoint-50/model.safetensors +3 -0
  9. clap_finetuned/checkpoint-50/optimizer.pt +3 -0
  10. clap_finetuned/checkpoint-50/rng_state.pth +3 -0
  11. clap_finetuned/checkpoint-50/scheduler.pt +3 -0
  12. clap_finetuned/checkpoint-50/trainer_state.json +96 -0
  13. clap_finetuned/checkpoint-50/training_args.bin +3 -0
  14. clap_finetuned/config.json +29 -0
  15. clap_finetuned/merges.txt +0 -0
  16. clap_finetuned/model.safetensors +3 -0
  17. clap_finetuned/preprocessor_config.json +22 -0
  18. clap_finetuned/special_tokens_map.json +51 -0
  19. clap_finetuned/tokenizer.json +0 -0
  20. clap_finetuned/tokenizer_config.json +62 -0
  21. clap_finetuned/vocab.json +0 -0
clap_finetuned/.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "laion/larger_clap_music_and_speech",
3
+ "architectures": [
4
+ "ClapModel"
5
+ ],
6
+ "audio_config": {
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 12,
11
+ 2
12
+ ],
13
+ "hidden_size": 1024,
14
+ "model_type": "clap_audio_model",
15
+ "patch_embeds_hidden_size": 128
16
+ },
17
+ "hidden_size": 768,
18
+ "initializer_factor": 1.0,
19
+ "logit_scale_init_value": 14.285714285714285,
20
+ "model_type": "clap",
21
+ "num_hidden_layers": 16,
22
+ "projection_dim": 512,
23
+ "projection_hidden_act": "relu",
24
+ "text_config": {
25
+ "model_type": "clap_text_model"
26
+ },
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.45.2"
29
+ }
clap_finetuned/.ipynb_checkpoints/merges-checkpoint.txt ADDED
The diff for this file is too large to render. See raw diff
 
clap_finetuned/.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
clap_finetuned/.ipynb_checkpoints/tokenizer_config-checkpoint.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
+ }
clap_finetuned/.ipynb_checkpoints/vocab-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
clap_finetuned/checkpoint-50/.ipynb_checkpoints/trainer_state-checkpoint.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_runtime": 3.8229,
14
+ "eval_samples_per_second": 41.853,
15
+ "eval_steps_per_second": 2.616,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_runtime": 3.8257,
21
+ "eval_samples_per_second": 41.823,
22
+ "eval_steps_per_second": 2.614,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 3.0,
27
+ "eval_runtime": 3.8314,
28
+ "eval_samples_per_second": 41.76,
29
+ "eval_steps_per_second": 2.61,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 4.0,
34
+ "eval_runtime": 3.7277,
35
+ "eval_samples_per_second": 42.921,
36
+ "eval_steps_per_second": 2.683,
37
+ "step": 40
38
+ }
39
+ ],
40
+ "logging_steps": 100,
41
+ "max_steps": 50,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 5,
44
+ "save_steps": 1000,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": true
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 3717956208000.0,
58
+ "train_batch_size": 16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
clap_finetuned/checkpoint-50/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "laion/larger_clap_music_and_speech",
3
+ "architectures": [
4
+ "ClapModel"
5
+ ],
6
+ "audio_config": {
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 12,
11
+ 2
12
+ ],
13
+ "hidden_size": 1024,
14
+ "model_type": "clap_audio_model",
15
+ "patch_embeds_hidden_size": 128
16
+ },
17
+ "hidden_size": 768,
18
+ "initializer_factor": 1.0,
19
+ "logit_scale_init_value": 14.285714285714285,
20
+ "model_type": "clap",
21
+ "num_hidden_layers": 16,
22
+ "projection_dim": 512,
23
+ "projection_hidden_act": "relu",
24
+ "text_config": {
25
+ "model_type": "clap_text_model"
26
+ },
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.45.2"
29
+ }
clap_finetuned/checkpoint-50/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37752657841fd16a6041b9a92e9d3b5a3138683c3b786e9d6f3890d7a3f471e2
3
+ size 776327440
clap_finetuned/checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f1e76a0e9f37165f2bef75e085d96507aa9cc4970d76ffdafbaf93152cf34f
3
+ size 1551756558
clap_finetuned/checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de470a7717ef6ccbfd7ba91a968a6cc1ad1d1c312467a9376bb17502f5f8d4fa
3
+ size 14244
clap_finetuned/checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
+ size 1064
clap_finetuned/checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 2.9972712993621826,
14
+ "learning_rate": 8e-05,
15
+ "loss": 1.8847,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_runtime": 3.7969,
21
+ "eval_samples_per_second": 42.14,
22
+ "eval_steps_per_second": 2.634,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "grad_norm": 2.789602756500244,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.7175,
30
+ "step": 20
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_runtime": 3.7066,
35
+ "eval_samples_per_second": 43.167,
36
+ "eval_steps_per_second": 2.698,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "grad_norm": 4.814621448516846,
42
+ "learning_rate": 4e-05,
43
+ "loss": 1.759,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_runtime": 3.82,
49
+ "eval_samples_per_second": 41.884,
50
+ "eval_steps_per_second": 2.618,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "grad_norm": 2.8232967853546143,
56
+ "learning_rate": 2e-05,
57
+ "loss": 1.8747,
58
+ "step": 40
59
+ },
60
+ {
61
+ "epoch": 4.0,
62
+ "eval_runtime": 3.7216,
63
+ "eval_samples_per_second": 42.993,
64
+ "eval_steps_per_second": 2.687,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 5.0,
69
+ "grad_norm": 2.186051368713379,
70
+ "learning_rate": 0.0,
71
+ "loss": 1.8117,
72
+ "step": 50
73
+ }
74
+ ],
75
+ "logging_steps": 10,
76
+ "max_steps": 50,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 5,
79
+ "save_steps": 200,
80
+ "stateful_callbacks": {
81
+ "TrainerControl": {
82
+ "args": {
83
+ "should_epoch_stop": false,
84
+ "should_evaluate": false,
85
+ "should_log": false,
86
+ "should_save": true,
87
+ "should_training_stop": true
88
+ },
89
+ "attributes": {}
90
+ }
91
+ },
92
+ "total_flos": 3717956208000.0,
93
+ "train_batch_size": 16,
94
+ "trial_name": null,
95
+ "trial_params": null
96
+ }
clap_finetuned/checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62530e9fec437c24aae2a82cbd86ca982b914586a6547d6cb1a7b318443611b9
3
+ size 5112
clap_finetuned/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "laion/larger_clap_music_and_speech",
3
+ "architectures": [
4
+ "ClapModel"
5
+ ],
6
+ "audio_config": {
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 12,
11
+ 2
12
+ ],
13
+ "hidden_size": 1024,
14
+ "model_type": "clap_audio_model",
15
+ "patch_embeds_hidden_size": 128
16
+ },
17
+ "hidden_size": 768,
18
+ "initializer_factor": 1.0,
19
+ "logit_scale_init_value": 14.285714285714285,
20
+ "model_type": "clap",
21
+ "num_hidden_layers": 16,
22
+ "projection_dim": 512,
23
+ "projection_hidden_act": "relu",
24
+ "text_config": {
25
+ "model_type": "clap_text_model"
26
+ },
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.45.2"
29
+ }
clap_finetuned/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
clap_finetuned/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc94e930daf50199d5156431e7d74cd600ef38d6bb05d4ac8a77d0c57ebc884d
3
+ size 776327440
clap_finetuned/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
+ }
clap_finetuned/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
+ }
clap_finetuned/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
clap_finetuned/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
+ }
clap_finetuned/vocab.json ADDED
The diff for this file is too large to render. See raw diff