HF中国镜像站's logo

Yassmen
/
Wav2Vec2_Fine_tuned_on_CremaD_Speech_Emotion_Recognition

Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Yassmen commited on
Commit
19fcc50
·
verified ·
1 Parent(s): dadea77

End of training

Browse files
Files changed (4) hide show
  1. README.md +162 -19
  2. model.safetensors +1 -1
  3. runs/Apr17_18-30-21_d3/events.out.tfevents.1713371443.d3.134742.0 +3 -0
  4. training_args.bin +2 -2
README.md CHANGED
@@ -3,33 +3,22 @@ license: apache-2.0
3
  base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
- - name: wav2vec2_crema_d_ser
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # Speech Emotion Recognition By Fine-Tuning Wav2Vec 2.0
15
-
16
- The model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) for a Speech Emotion Recognition (SER) task.
17
-
18
- The dataset used to fine-tune the original pre-trained model is the [Crema-D dataset](https://github.com/CheyneyComputerScience/CREMA-D). This dataset provides 7442 samples of recordings from actors performing on 6 different emotions in English, which are:
19
-
20
- ```python
21
- emotions = ['angry', 'disgust', 'fear', 'happy', 'neutral', 'sad']
22
- ```
23
-
24
 
 
25
  It achieves the following results on the evaluation set:
26
- - eval_loss: 0.7449
27
- - eval_accuracy: 0.7211
28
- - eval_runtime: 93.9018
29
- - eval_samples_per_second: 15.846
30
- - eval_steps_per_second: 3.962
31
- - epoch: 0.86
32
- - step: 640
33
 
34
  ## Model description
35
 
@@ -56,9 +45,163 @@ The following hyperparameters were used during training:
56
  - total_train_batch_size: 8
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
- - num_epochs: 1.0
60
  - mixed_precision_training: Native AMP
61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  ### Framework versions
63
 
64
  - Transformers 4.40.0.dev0
 
3
  base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
  model-index:
9
+ - name: Wav2Vec2_Fine_tuned_on_CremaD_Speech_Emotion_Recognition
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # Wav2Vec2_Fine_tuned_on_CremaD_Speech_Emotion_Recognition
 
 
 
 
 
 
 
 
 
17
 
18
+ This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6258
21
+ - Accuracy: 0.7890
 
 
 
 
 
22
 
23
  ## Model description
24
 
 
45
  - total_train_batch_size: 8
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 2.0
49
  - mixed_precision_training: Native AMP
50
 
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 1.7923 | 0.01 | 10 | 1.8102 | 0.2554 |
56
+ | 1.7712 | 0.03 | 20 | 1.7128 | 0.2560 |
57
+ | 1.6854 | 0.04 | 30 | 1.7213 | 0.2823 |
58
+ | 1.6129 | 0.05 | 40 | 1.5384 | 0.3851 |
59
+ | 1.5121 | 0.07 | 50 | 1.5442 | 0.3810 |
60
+ | 1.532 | 0.08 | 60 | 1.4817 | 0.4234 |
61
+ | 1.3681 | 0.09 | 70 | 1.6103 | 0.3474 |
62
+ | 1.6408 | 0.11 | 80 | 1.5118 | 0.3495 |
63
+ | 1.4527 | 0.12 | 90 | 1.3684 | 0.4671 |
64
+ | 1.3219 | 0.13 | 100 | 1.3871 | 0.4698 |
65
+ | 1.5121 | 0.15 | 110 | 1.4060 | 0.4328 |
66
+ | 1.4013 | 0.16 | 120 | 1.5057 | 0.4180 |
67
+ | 1.3605 | 0.17 | 130 | 1.3576 | 0.4348 |
68
+ | 1.3813 | 0.19 | 140 | 1.3194 | 0.4933 |
69
+ | 1.2232 | 0.2 | 150 | 1.2804 | 0.5114 |
70
+ | 1.3133 | 0.22 | 160 | 1.2345 | 0.5356 |
71
+ | 1.2686 | 0.23 | 170 | 1.2445 | 0.5161 |
72
+ | 1.2539 | 0.24 | 180 | 1.1071 | 0.5766 |
73
+ | 1.1747 | 0.26 | 190 | 1.2424 | 0.5060 |
74
+ | 1.1644 | 0.27 | 200 | 1.3082 | 0.4892 |
75
+ | 1.2624 | 0.28 | 210 | 1.3811 | 0.5155 |
76
+ | 1.2036 | 0.3 | 220 | 1.2410 | 0.5349 |
77
+ | 1.2191 | 0.31 | 230 | 1.0329 | 0.5988 |
78
+ | 1.1212 | 0.32 | 240 | 1.1005 | 0.5806 |
79
+ | 1.1243 | 0.34 | 250 | 1.2593 | 0.5262 |
80
+ | 1.1951 | 0.35 | 260 | 1.0575 | 0.5981 |
81
+ | 1.0971 | 0.36 | 270 | 1.1753 | 0.5565 |
82
+ | 1.0209 | 0.38 | 280 | 1.0568 | 0.5840 |
83
+ | 1.1628 | 0.39 | 290 | 1.1174 | 0.5793 |
84
+ | 1.1894 | 0.4 | 300 | 1.0343 | 0.6183 |
85
+ | 1.0605 | 0.42 | 310 | 1.1357 | 0.5578 |
86
+ | 1.0701 | 0.43 | 320 | 1.0726 | 0.6042 |
87
+ | 0.9606 | 0.44 | 330 | 1.2933 | 0.5222 |
88
+ | 0.9128 | 0.46 | 340 | 1.1310 | 0.5827 |
89
+ | 1.1218 | 0.47 | 350 | 1.1245 | 0.6102 |
90
+ | 0.9566 | 0.48 | 360 | 1.0386 | 0.6116 |
91
+ | 1.1211 | 0.5 | 370 | 0.9842 | 0.6324 |
92
+ | 1.2184 | 0.51 | 380 | 0.9250 | 0.6593 |
93
+ | 1.1452 | 0.52 | 390 | 0.9282 | 0.6573 |
94
+ | 0.7752 | 0.54 | 400 | 1.0523 | 0.6102 |
95
+ | 1.0063 | 0.55 | 410 | 0.9372 | 0.6364 |
96
+ | 1.1807 | 0.56 | 420 | 1.0236 | 0.6176 |
97
+ | 1.0624 | 0.58 | 430 | 0.9036 | 0.6606 |
98
+ | 1.1832 | 0.59 | 440 | 0.9229 | 0.6458 |
99
+ | 1.0186 | 0.6 | 450 | 0.8801 | 0.6707 |
100
+ | 0.8184 | 0.62 | 460 | 0.9526 | 0.6398 |
101
+ | 0.8863 | 0.63 | 470 | 0.8996 | 0.6761 |
102
+ | 0.9068 | 0.65 | 480 | 0.8378 | 0.7030 |
103
+ | 0.8077 | 0.66 | 490 | 0.9574 | 0.6694 |
104
+ | 0.9824 | 0.67 | 500 | 1.0673 | 0.6499 |
105
+ | 0.8002 | 0.69 | 510 | 0.8819 | 0.6922 |
106
+ | 0.9411 | 0.7 | 520 | 0.8553 | 0.6815 |
107
+ | 1.0061 | 0.71 | 530 | 0.9180 | 0.6673 |
108
+ | 0.7496 | 0.73 | 540 | 0.9676 | 0.6505 |
109
+ | 0.8208 | 0.74 | 550 | 0.9990 | 0.6519 |
110
+ | 0.9846 | 0.75 | 560 | 0.8613 | 0.6962 |
111
+ | 0.9968 | 0.77 | 570 | 0.8798 | 0.6949 |
112
+ | 0.9485 | 0.78 | 580 | 0.9894 | 0.6223 |
113
+ | 0.9165 | 0.79 | 590 | 0.9384 | 0.6465 |
114
+ | 0.9393 | 0.81 | 600 | 0.7944 | 0.7137 |
115
+ | 0.9086 | 0.82 | 610 | 0.8543 | 0.6767 |
116
+ | 0.9175 | 0.83 | 620 | 0.8039 | 0.6996 |
117
+ | 0.8692 | 0.85 | 630 | 0.8488 | 0.6949 |
118
+ | 0.759 | 0.86 | 640 | 0.8890 | 0.6895 |
119
+ | 1.0115 | 0.87 | 650 | 1.0963 | 0.6210 |
120
+ | 0.766 | 0.89 | 660 | 0.9505 | 0.6277 |
121
+ | 1.2062 | 0.9 | 670 | 0.8218 | 0.6962 |
122
+ | 0.8678 | 0.91 | 680 | 0.7918 | 0.7056 |
123
+ | 0.9055 | 0.93 | 690 | 0.7626 | 0.7204 |
124
+ | 0.7303 | 0.94 | 700 | 0.8733 | 0.6714 |
125
+ | 0.9239 | 0.95 | 710 | 0.8488 | 0.6962 |
126
+ | 0.8024 | 0.97 | 720 | 0.7996 | 0.7083 |
127
+ | 0.7927 | 0.98 | 730 | 0.8690 | 0.6821 |
128
+ | 0.8371 | 0.99 | 740 | 0.9029 | 0.6727 |
129
+ | 0.8419 | 1.01 | 750 | 0.7640 | 0.7211 |
130
+ | 0.5163 | 1.02 | 760 | 0.8040 | 0.7292 |
131
+ | 0.4603 | 1.03 | 770 | 0.7946 | 0.7211 |
132
+ | 0.7675 | 1.05 | 780 | 0.9796 | 0.6774 |
133
+ | 0.9771 | 1.06 | 790 | 0.7548 | 0.7433 |
134
+ | 0.6141 | 1.08 | 800 | 0.7334 | 0.7386 |
135
+ | 0.71 | 1.09 | 810 | 0.7037 | 0.7547 |
136
+ | 0.6074 | 1.1 | 820 | 0.8142 | 0.7137 |
137
+ | 1.0638 | 1.12 | 830 | 0.8786 | 0.7036 |
138
+ | 0.7303 | 1.13 | 840 | 0.7548 | 0.7292 |
139
+ | 0.5361 | 1.14 | 850 | 0.7000 | 0.7513 |
140
+ | 0.6014 | 1.16 | 860 | 0.8950 | 0.6902 |
141
+ | 0.5635 | 1.17 | 870 | 0.7070 | 0.75 |
142
+ | 0.5585 | 1.18 | 880 | 0.7612 | 0.7473 |
143
+ | 0.8462 | 1.2 | 890 | 1.0107 | 0.6761 |
144
+ | 0.6256 | 1.21 | 900 | 0.7899 | 0.7272 |
145
+ | 0.7361 | 1.22 | 910 | 0.7397 | 0.7312 |
146
+ | 0.5147 | 1.24 | 920 | 0.8835 | 0.7003 |
147
+ | 0.5843 | 1.25 | 930 | 0.8751 | 0.7016 |
148
+ | 0.5077 | 1.26 | 940 | 0.7542 | 0.7278 |
149
+ | 0.6421 | 1.28 | 950 | 0.8593 | 0.7090 |
150
+ | 0.7138 | 1.29 | 960 | 0.7012 | 0.7601 |
151
+ | 0.5414 | 1.3 | 970 | 0.7669 | 0.7372 |
152
+ | 0.662 | 1.32 | 980 | 0.7620 | 0.7272 |
153
+ | 0.6002 | 1.33 | 990 | 0.6881 | 0.7628 |
154
+ | 0.8094 | 1.34 | 1000 | 0.7783 | 0.7433 |
155
+ | 0.6081 | 1.36 | 1010 | 0.7272 | 0.75 |
156
+ | 0.5943 | 1.37 | 1020 | 0.7667 | 0.7440 |
157
+ | 0.6295 | 1.38 | 1030 | 0.7453 | 0.7399 |
158
+ | 0.6415 | 1.4 | 1040 | 0.7053 | 0.7560 |
159
+ | 0.4686 | 1.41 | 1050 | 0.8764 | 0.7171 |
160
+ | 0.5586 | 1.42 | 1060 | 0.7406 | 0.75 |
161
+ | 0.4292 | 1.44 | 1070 | 0.7160 | 0.7708 |
162
+ | 0.6343 | 1.45 | 1080 | 0.8051 | 0.7298 |
163
+ | 0.6209 | 1.47 | 1090 | 0.9153 | 0.7198 |
164
+ | 0.834 | 1.48 | 1100 | 0.7113 | 0.7614 |
165
+ | 0.5106 | 1.49 | 1110 | 0.7978 | 0.7352 |
166
+ | 0.6587 | 1.51 | 1120 | 0.7805 | 0.7440 |
167
+ | 0.5694 | 1.52 | 1130 | 0.7192 | 0.7587 |
168
+ | 0.6949 | 1.53 | 1140 | 0.7119 | 0.7614 |
169
+ | 0.4578 | 1.55 | 1150 | 0.7249 | 0.7594 |
170
+ | 0.6219 | 1.56 | 1160 | 0.7289 | 0.7554 |
171
+ | 0.6857 | 1.57 | 1170 | 0.6933 | 0.7587 |
172
+ | 0.631 | 1.59 | 1180 | 0.6719 | 0.7749 |
173
+ | 0.6944 | 1.6 | 1190 | 0.7028 | 0.7587 |
174
+ | 0.5063 | 1.61 | 1200 | 0.6815 | 0.7587 |
175
+ | 0.6884 | 1.63 | 1210 | 0.7068 | 0.7534 |
176
+ | 0.797 | 1.64 | 1220 | 0.7583 | 0.7426 |
177
+ | 0.5841 | 1.65 | 1230 | 0.7034 | 0.7446 |
178
+ | 0.7062 | 1.67 | 1240 | 0.7050 | 0.7513 |
179
+ | 0.7438 | 1.68 | 1250 | 0.6894 | 0.7560 |
180
+ | 0.6627 | 1.69 | 1260 | 0.6438 | 0.7769 |
181
+ | 0.4233 | 1.71 | 1270 | 0.6523 | 0.7695 |
182
+ | 0.5555 | 1.72 | 1280 | 0.6859 | 0.7634 |
183
+ | 0.7625 | 1.73 | 1290 | 0.7076 | 0.7513 |
184
+ | 0.6136 | 1.75 | 1300 | 0.6515 | 0.7769 |
185
+ | 0.5207 | 1.76 | 1310 | 0.6463 | 0.7708 |
186
+ | 0.5175 | 1.77 | 1320 | 0.6442 | 0.7762 |
187
+ | 0.6413 | 1.79 | 1330 | 0.6515 | 0.7742 |
188
+ | 0.7482 | 1.8 | 1340 | 0.6608 | 0.7735 |
189
+ | 0.5284 | 1.81 | 1350 | 0.6717 | 0.7681 |
190
+ | 0.7004 | 1.83 | 1360 | 0.6800 | 0.7628 |
191
+ | 0.7958 | 1.84 | 1370 | 0.6577 | 0.7769 |
192
+ | 0.3887 | 1.85 | 1380 | 0.6428 | 0.7829 |
193
+ | 0.4225 | 1.87 | 1390 | 0.6465 | 0.7809 |
194
+ | 0.7193 | 1.88 | 1400 | 0.6590 | 0.7776 |
195
+ | 0.5101 | 1.9 | 1410 | 0.6519 | 0.7789 |
196
+ | 0.7712 | 1.91 | 1420 | 0.6510 | 0.7789 |
197
+ | 0.3919 | 1.92 | 1430 | 0.6566 | 0.7809 |
198
+ | 0.4867 | 1.94 | 1440 | 0.6531 | 0.7755 |
199
+ | 0.5402 | 1.95 | 1450 | 0.6441 | 0.7789 |
200
+ | 0.7002 | 1.96 | 1460 | 0.6344 | 0.7809 |
201
+ | 0.5943 | 1.98 | 1470 | 0.6278 | 0.7870 |
202
+ | 0.5144 | 1.99 | 1480 | 0.6258 | 0.7890 |
203
+
204
+
205
  ### Framework versions
206
 
207
  - Transformers 4.40.0.dev0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d14acc4bd5a35b234fa9f130f26ecd7b0c4b52d93bbae07157256d5fdb8ccd90
3
  size 1266030704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d5760ff296f20223509da35ea6f795a544ae1c0df6eba87568c92afe72ebae
3
  size 1266030704
runs/Apr17_18-30-21_d3/events.out.tfevents.1713371443.d3.134742.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c8d4b60ef1ee7e168862da4c69f4860a7cbba0299c95ea99c7317f14d4bbe3
3
+ size 85940
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbb61568eef2d2214abd81d877b03191362d71af0e88a130c0ecd75ab8cbbfc5
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5105573d771914e7d0e1eaec4f65986116d4a3684e0be84a85d6011b34e8420c
3
+ size 4984