first
Browse files- README.md +87 -0
- config.json +186 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/Nov27_09-41-10_34627fe27eea/events.out.tfevents.1701078076.34627fe27eea.47.0 +3 -0
- runs/Nov27_09-51-53_34627fe27eea/events.out.tfevents.1701078716.34627fe27eea.47.1 +3 -0
- runs/Nov27_09-57-50_34627fe27eea/events.out.tfevents.1701079071.34627fe27eea.47.2 +3 -0
- runs/Nov27_09-59-31_34627fe27eea/events.out.tfevents.1701079172.34627fe27eea.47.3 +3 -0
- runs/Nov27_10-01-39_34627fe27eea/events.out.tfevents.1701079300.34627fe27eea.47.4 +3 -0
- runs/Nov27_10-02-55_34627fe27eea/events.out.tfevents.1701079377.34627fe27eea.47.5 +3 -0
- runs/Nov27_10-03-21_34627fe27eea/events.out.tfevents.1701079406.34627fe27eea.47.6 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- audiofolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: my_awesome_mind_model
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Audio Classification
|
15 |
+
type: audio-classification
|
16 |
+
dataset:
|
17 |
+
name: audiofolder
|
18 |
+
type: audiofolder
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9805375347544022
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# my_awesome_mind_model
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1816
|
36 |
+
- Accuracy: 0.9805
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 3e-05
|
56 |
+
- train_batch_size: 128
|
57 |
+
- eval_batch_size: 128
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 512
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 10
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 2.267 | 1.0 | 120 | 2.0147 | 0.9626 |
|
71 |
+
| 1.309 | 2.0 | 240 | 1.0828 | 0.9731 |
|
72 |
+
| 0.8739 | 2.99 | 360 | 0.6753 | 0.9759 |
|
73 |
+
| 0.6183 | 4.0 | 481 | 0.4492 | 0.9781 |
|
74 |
+
| 0.4868 | 5.0 | 601 | 0.3346 | 0.9771 |
|
75 |
+
| 0.4124 | 6.0 | 721 | 0.2606 | 0.9787 |
|
76 |
+
| 0.3495 | 6.99 | 841 | 0.2214 | 0.9808 |
|
77 |
+
| 0.3073 | 8.0 | 962 | 0.2032 | 0.9790 |
|
78 |
+
| 0.3264 | 9.0 | 1082 | 0.1862 | 0.9812 |
|
79 |
+
| 0.3035 | 9.98 | 1200 | 0.1816 | 0.9805 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.35.2
|
85 |
+
- Pytorch 2.0.0
|
86 |
+
- Datasets 2.15.0
|
87 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_attn_dim": null,
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": true,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2ForSequenceClassification"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
18 |
+
"conv_dim": [
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512
|
26 |
+
],
|
27 |
+
"conv_kernel": [
|
28 |
+
10,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
3,
|
33 |
+
2,
|
34 |
+
2
|
35 |
+
],
|
36 |
+
"conv_stride": [
|
37 |
+
5,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2,
|
43 |
+
2
|
44 |
+
],
|
45 |
+
"ctc_loss_reduction": "sum",
|
46 |
+
"ctc_zero_infinity": false,
|
47 |
+
"diversity_loss_weight": 0.1,
|
48 |
+
"do_stable_layer_norm": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"id2label": {
|
60 |
+
"0": "_background_noise_",
|
61 |
+
"1": "audio",
|
62 |
+
"10": "go",
|
63 |
+
"11": "happy",
|
64 |
+
"12": "house",
|
65 |
+
"13": "left",
|
66 |
+
"14": "marvin",
|
67 |
+
"15": "nine",
|
68 |
+
"16": "no",
|
69 |
+
"17": "off",
|
70 |
+
"18": "on",
|
71 |
+
"19": "one",
|
72 |
+
"2": "bed",
|
73 |
+
"20": "right",
|
74 |
+
"21": "seven",
|
75 |
+
"22": "sheila",
|
76 |
+
"23": "six",
|
77 |
+
"24": "stop",
|
78 |
+
"25": "three",
|
79 |
+
"26": "tree",
|
80 |
+
"27": "two",
|
81 |
+
"28": "up",
|
82 |
+
"29": "wow",
|
83 |
+
"3": "bird",
|
84 |
+
"30": "yes",
|
85 |
+
"31": "zero",
|
86 |
+
"4": "cat",
|
87 |
+
"5": "dog",
|
88 |
+
"6": "down",
|
89 |
+
"7": "eight",
|
90 |
+
"8": "five",
|
91 |
+
"9": "four"
|
92 |
+
},
|
93 |
+
"initializer_range": 0.02,
|
94 |
+
"intermediate_size": 3072,
|
95 |
+
"label2id": {
|
96 |
+
"_background_noise_": "0",
|
97 |
+
"audio": "1",
|
98 |
+
"bed": "2",
|
99 |
+
"bird": "3",
|
100 |
+
"cat": "4",
|
101 |
+
"dog": "5",
|
102 |
+
"down": "6",
|
103 |
+
"eight": "7",
|
104 |
+
"five": "8",
|
105 |
+
"four": "9",
|
106 |
+
"go": "10",
|
107 |
+
"happy": "11",
|
108 |
+
"house": "12",
|
109 |
+
"left": "13",
|
110 |
+
"marvin": "14",
|
111 |
+
"nine": "15",
|
112 |
+
"no": "16",
|
113 |
+
"off": "17",
|
114 |
+
"on": "18",
|
115 |
+
"one": "19",
|
116 |
+
"right": "20",
|
117 |
+
"seven": "21",
|
118 |
+
"sheila": "22",
|
119 |
+
"six": "23",
|
120 |
+
"stop": "24",
|
121 |
+
"three": "25",
|
122 |
+
"tree": "26",
|
123 |
+
"two": "27",
|
124 |
+
"up": "28",
|
125 |
+
"wow": "29",
|
126 |
+
"yes": "30",
|
127 |
+
"zero": "31"
|
128 |
+
},
|
129 |
+
"layer_norm_eps": 1e-05,
|
130 |
+
"layerdrop": 0.0,
|
131 |
+
"mask_channel_length": 10,
|
132 |
+
"mask_channel_min_space": 1,
|
133 |
+
"mask_channel_other": 0.0,
|
134 |
+
"mask_channel_prob": 0.0,
|
135 |
+
"mask_channel_selection": "static",
|
136 |
+
"mask_feature_length": 10,
|
137 |
+
"mask_feature_min_masks": 0,
|
138 |
+
"mask_feature_prob": 0.0,
|
139 |
+
"mask_time_length": 10,
|
140 |
+
"mask_time_min_masks": 2,
|
141 |
+
"mask_time_min_space": 1,
|
142 |
+
"mask_time_other": 0.0,
|
143 |
+
"mask_time_prob": 0.05,
|
144 |
+
"mask_time_selection": "static",
|
145 |
+
"model_type": "wav2vec2",
|
146 |
+
"no_mask_channel_overlap": false,
|
147 |
+
"no_mask_time_overlap": false,
|
148 |
+
"num_adapter_layers": 3,
|
149 |
+
"num_attention_heads": 12,
|
150 |
+
"num_codevector_groups": 2,
|
151 |
+
"num_codevectors_per_group": 320,
|
152 |
+
"num_conv_pos_embedding_groups": 16,
|
153 |
+
"num_conv_pos_embeddings": 128,
|
154 |
+
"num_feat_extract_layers": 7,
|
155 |
+
"num_hidden_layers": 12,
|
156 |
+
"num_negatives": 100,
|
157 |
+
"output_hidden_size": 768,
|
158 |
+
"pad_token_id": 0,
|
159 |
+
"proj_codevector_dim": 256,
|
160 |
+
"tdnn_dilation": [
|
161 |
+
1,
|
162 |
+
2,
|
163 |
+
3,
|
164 |
+
1,
|
165 |
+
1
|
166 |
+
],
|
167 |
+
"tdnn_dim": [
|
168 |
+
512,
|
169 |
+
512,
|
170 |
+
512,
|
171 |
+
512,
|
172 |
+
1500
|
173 |
+
],
|
174 |
+
"tdnn_kernel": [
|
175 |
+
5,
|
176 |
+
3,
|
177 |
+
3,
|
178 |
+
1,
|
179 |
+
1
|
180 |
+
],
|
181 |
+
"torch_dtype": "float32",
|
182 |
+
"transformers_version": "4.35.2",
|
183 |
+
"use_weighted_layer_sum": false,
|
184 |
+
"vocab_size": 32,
|
185 |
+
"xvector_output_dim": 512
|
186 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:373af34163799ac9cf8cbfc0af69b298dc291e604aee8cafdad7aacd349cfe43
|
3 |
+
size 378333160
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
runs/Nov27_09-41-10_34627fe27eea/events.out.tfevents.1701078076.34627fe27eea.47.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d413a9d67493d97d2c90d72e62e1a1969487ea186c9479e78b038c3736b6d4a
|
3 |
+
size 7133
|
runs/Nov27_09-51-53_34627fe27eea/events.out.tfevents.1701078716.34627fe27eea.47.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf3bd9e881f2a23e0c1be3c97a0429bb00a1977f87b905ea5cc09654f1fc3ffb
|
3 |
+
size 7133
|
runs/Nov27_09-57-50_34627fe27eea/events.out.tfevents.1701079071.34627fe27eea.47.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9eb63a3a3bfed7b3a96ec04c367c183cc45672862a1a5063f8738bd608d97f84
|
3 |
+
size 7133
|
runs/Nov27_09-59-31_34627fe27eea/events.out.tfevents.1701079172.34627fe27eea.47.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf73179fd80a5fafa3731d629b38f4788fa45c781421ff427cdf56f9da52e960
|
3 |
+
size 7133
|
runs/Nov27_10-01-39_34627fe27eea/events.out.tfevents.1701079300.34627fe27eea.47.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc05ede20c35a99cd1b2c8a548cf7fc8127bf2ab8481d2a5d060277278b8a195
|
3 |
+
size 7450
|
runs/Nov27_10-02-55_34627fe27eea/events.out.tfevents.1701079377.34627fe27eea.47.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70388112a08f4687bd1b70aa3a6a59722b2383536e4d385ba7ab869499a8fa93
|
3 |
+
size 7133
|
runs/Nov27_10-03-21_34627fe27eea/events.out.tfevents.1701079406.34627fe27eea.47.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2312dfb87ddaedfbbc5bb6c8a78b7294c22331a75c0bedb29a92bdbc1d3c70b6
|
3 |
+
size 29518
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54c50b06da89a4db2ba6e3554e1b16d847ff7b6f7f1144f316e04be878cb1820
|
3 |
+
size 4155
|