End of training
Browse files- README.md +80 -0
- config.json +185 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/Dec18_18-20-18_DESKTOP-RI439S7/events.out.tfevents.1702894880.DESKTOP-RI439S7.5944.0 +3 -0
- runs/Dec18_18-54-46_DESKTOP-RI439S7/events.out.tfevents.1702896888.DESKTOP-RI439S7.2816.0 +3 -0
- runs/Dec18_18-55-42_DESKTOP-RI439S7/events.out.tfevents.1702896944.DESKTOP-RI439S7.12900.0 +3 -0
- runs/Dec18_18-57-08_DESKTOP-RI439S7/events.out.tfevents.1702897029.DESKTOP-RI439S7.13084.0 +3 -0
- runs/Dec18_18-58-26_DESKTOP-RI439S7/events.out.tfevents.1702897107.DESKTOP-RI439S7.12480.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- speech_commands
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-speechcommonds-kws
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Audio Classification
|
13 |
+
type: audio-classification
|
14 |
+
dataset:
|
15 |
+
name: speech_commands
|
16 |
+
type: speech_commands
|
17 |
+
config: v0.02
|
18 |
+
split: test
|
19 |
+
args: v0.02
|
20 |
+
metrics:
|
21 |
+
- name: Accuracy
|
22 |
+
type: accuracy
|
23 |
+
value: 0.9854975457385096
|
24 |
+
---
|
25 |
+
|
26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
27 |
+
should probably proofread and complete it, then remove this comment. -->
|
28 |
+
|
29 |
+
# wav2vec2-speechcommonds-kws
|
30 |
+
|
31 |
+
This model was trained from scratch on the speech_commands dataset.
|
32 |
+
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.0613
|
34 |
+
- Accuracy: 0.9855
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 3e-05
|
54 |
+
- train_batch_size: 32
|
55 |
+
- eval_batch_size: 32
|
56 |
+
- seed: 42
|
57 |
+
- gradient_accumulation_steps: 4
|
58 |
+
- total_train_batch_size: 128
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
62 |
+
- num_epochs: 5
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 1.0871 | 1.0 | 741 | 0.3374 | 0.9810 |
|
69 |
+
| 0.5168 | 2.0 | 1482 | 0.1022 | 0.9866 |
|
70 |
+
| 0.4113 | 3.0 | 2223 | 0.0766 | 0.9853 |
|
71 |
+
| 0.3622 | 4.0 | 2964 | 0.0670 | 0.9859 |
|
72 |
+
| 0.3454 | 5.0 | 3705 | 0.0613 | 0.9855 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.36.1
|
78 |
+
- Pytorch 2.1.1
|
79 |
+
- Datasets 2.15.0
|
80 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "D:/AudioClassification/wav2vec2-large-960h-lv60",
|
3 |
+
"activation_dropout": 0.1,
|
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": true,
|
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": true,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_dropout": 0.0,
|
52 |
+
"feat_extract_norm": "layer",
|
53 |
+
"feat_proj_dropout": 0.0,
|
54 |
+
"feat_quantizer_dropout": 0.0,
|
55 |
+
"final_dropout": 0.1,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 1024,
|
60 |
+
"id2label": {
|
61 |
+
"0": "yes",
|
62 |
+
"1": "no",
|
63 |
+
"10": "zero",
|
64 |
+
"11": "one",
|
65 |
+
"12": "two",
|
66 |
+
"13": "three",
|
67 |
+
"14": "four",
|
68 |
+
"15": "five",
|
69 |
+
"16": "six",
|
70 |
+
"17": "seven",
|
71 |
+
"18": "eight",
|
72 |
+
"19": "nine",
|
73 |
+
"2": "up",
|
74 |
+
"20": "bed",
|
75 |
+
"21": "bird",
|
76 |
+
"22": "cat",
|
77 |
+
"23": "dog",
|
78 |
+
"24": "happy",
|
79 |
+
"25": "house",
|
80 |
+
"26": "marvin",
|
81 |
+
"27": "sheila",
|
82 |
+
"28": "tree",
|
83 |
+
"29": "wow",
|
84 |
+
"3": "down",
|
85 |
+
"30": "backward",
|
86 |
+
"31": "forward",
|
87 |
+
"32": "follow",
|
88 |
+
"33": "learn",
|
89 |
+
"34": "visual",
|
90 |
+
"35": "_silence_",
|
91 |
+
"4": "left",
|
92 |
+
"5": "right",
|
93 |
+
"6": "on",
|
94 |
+
"7": "off",
|
95 |
+
"8": "stop",
|
96 |
+
"9": "go"
|
97 |
+
},
|
98 |
+
"initializer_range": 0.02,
|
99 |
+
"intermediate_size": 4096,
|
100 |
+
"label2id": {
|
101 |
+
"_silence_": "35",
|
102 |
+
"backward": "30",
|
103 |
+
"bed": "20",
|
104 |
+
"bird": "21",
|
105 |
+
"cat": "22",
|
106 |
+
"dog": "23",
|
107 |
+
"down": "3",
|
108 |
+
"eight": "18",
|
109 |
+
"five": "15",
|
110 |
+
"follow": "32",
|
111 |
+
"forward": "31",
|
112 |
+
"four": "14",
|
113 |
+
"go": "9",
|
114 |
+
"happy": "24",
|
115 |
+
"house": "25",
|
116 |
+
"learn": "33",
|
117 |
+
"left": "4",
|
118 |
+
"marvin": "26",
|
119 |
+
"nine": "19",
|
120 |
+
"no": "1",
|
121 |
+
"off": "7",
|
122 |
+
"on": "6",
|
123 |
+
"one": "11",
|
124 |
+
"right": "5",
|
125 |
+
"seven": "17",
|
126 |
+
"sheila": "27",
|
127 |
+
"six": "16",
|
128 |
+
"stop": "8",
|
129 |
+
"three": "13",
|
130 |
+
"tree": "28",
|
131 |
+
"two": "12",
|
132 |
+
"up": "2",
|
133 |
+
"visual": "34",
|
134 |
+
"wow": "29",
|
135 |
+
"yes": "0",
|
136 |
+
"zero": "10"
|
137 |
+
},
|
138 |
+
"layer_norm_eps": 1e-05,
|
139 |
+
"layerdrop": 0.1,
|
140 |
+
"mask_feature_length": 10,
|
141 |
+
"mask_feature_min_masks": 0,
|
142 |
+
"mask_feature_prob": 0.0,
|
143 |
+
"mask_time_length": 10,
|
144 |
+
"mask_time_min_masks": 2,
|
145 |
+
"mask_time_prob": 0.05,
|
146 |
+
"model_type": "wav2vec2",
|
147 |
+
"num_adapter_layers": 3,
|
148 |
+
"num_attention_heads": 16,
|
149 |
+
"num_codevector_groups": 2,
|
150 |
+
"num_codevectors_per_group": 320,
|
151 |
+
"num_conv_pos_embedding_groups": 16,
|
152 |
+
"num_conv_pos_embeddings": 128,
|
153 |
+
"num_feat_extract_layers": 7,
|
154 |
+
"num_hidden_layers": 24,
|
155 |
+
"num_negatives": 100,
|
156 |
+
"output_hidden_size": 1024,
|
157 |
+
"pad_token_id": 0,
|
158 |
+
"proj_codevector_dim": 256,
|
159 |
+
"tdnn_dilation": [
|
160 |
+
1,
|
161 |
+
2,
|
162 |
+
3,
|
163 |
+
1,
|
164 |
+
1
|
165 |
+
],
|
166 |
+
"tdnn_dim": [
|
167 |
+
512,
|
168 |
+
512,
|
169 |
+
512,
|
170 |
+
512,
|
171 |
+
1500
|
172 |
+
],
|
173 |
+
"tdnn_kernel": [
|
174 |
+
5,
|
175 |
+
3,
|
176 |
+
3,
|
177 |
+
1,
|
178 |
+
1
|
179 |
+
],
|
180 |
+
"torch_dtype": "float32",
|
181 |
+
"transformers_version": "4.36.1",
|
182 |
+
"use_weighted_layer_sum": false,
|
183 |
+
"vocab_size": 32,
|
184 |
+
"xvector_output_dim": 512
|
185 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e71e2ce87d6cdd8ca6e7256c4566fce56b2ea02d1c4587fa0f604d21b373707
|
3 |
+
size 1262894264
|
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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
runs/Dec18_18-20-18_DESKTOP-RI439S7/events.out.tfevents.1702894880.DESKTOP-RI439S7.5944.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a9e3f0af6389952e331091a62d8090285b80538732a54857d6b8e8979126eeb
|
3 |
+
size 101421
|
runs/Dec18_18-54-46_DESKTOP-RI439S7/events.out.tfevents.1702896888.DESKTOP-RI439S7.2816.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9429acc6a856378bba13d9fca4649aab29f0ec62f068c37fa64ba1cb6d034a63
|
3 |
+
size 7689
|
runs/Dec18_18-55-42_DESKTOP-RI439S7/events.out.tfevents.1702896944.DESKTOP-RI439S7.12900.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:550808f9889b0d5fbbccbce407525424bbe10e70f81eec398349d3a4a89e543d
|
3 |
+
size 7383
|
runs/Dec18_18-57-08_DESKTOP-RI439S7/events.out.tfevents.1702897029.DESKTOP-RI439S7.13084.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9f4d900add4e80ee75ab892bc648f4ae75421571557dec1f9dc061f78973aac
|
3 |
+
size 7691
|
runs/Dec18_18-58-26_DESKTOP-RI439S7/events.out.tfevents.1702897107.DESKTOP-RI439S7.12480.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99aa4af7bb93454d1570480be6e285568d19428916d86f8eb62d2515cee730a6
|
3 |
+
size 20810
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7788e2631d0abdc7de2b348f08ee0dc8310702d79b27dd689adf8a3b7f246cbe
|
3 |
+
size 4792
|