Hugging Face's logo

Zarakun
/
wav2vec

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
Zarakun commited on
Commit
997a82b
·
verified ·
1 Parent(s): d0f4f0f

zarakun/wav2vec

Browse files
Files changed (5) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. runs/Nov24_14-28-16_0e7bc815b640/events.out.tfevents.1732458503.0e7bc815b640.30.0 +3 -0
  4. runs/Nov24_14-28-16_0e7bc815b640/events.out.tfevents.1732459998.0e7bc815b640.30.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -24,10 +24,10 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.8909444985394352
28
  - name: F1
29
  type: f1
30
- value: 0.8408887171290298
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,9 +37,9 @@ should probably proofread and complete it, then remove this comment. -->
37
 
38
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the speech_commands dataset.
39
  It achieves the following results on the evaluation set:
40
- - Loss: 0.8904
41
- - Accuracy: 0.8909
42
- - F1: 0.8409
43
 
44
  ## Model description
45
 
@@ -58,7 +58,7 @@ More information needed
58
  ### Training hyperparameters
59
 
60
  The following hyperparameters were used during training:
61
- - learning_rate: 3e-05
62
  - train_batch_size: 240
63
  - eval_batch_size: 240
64
  - seed: 42
@@ -70,9 +70,9 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
- | 1.4272 | 1.0 | 213 | 1.3926 | 0.8845 | 0.8359 |
74
- | 0.9354 | 2.0 | 426 | 0.9938 | 0.8877 | 0.8598 |
75
- | 0.7761 | 3.0 | 639 | 0.8904 | 0.8909 | 0.8409 |
76
 
77
 
78
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.083089905874716
28
  - name: F1
29
  type: f1
30
+ value: 0.004949394375863969
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
37
 
38
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the speech_commands dataset.
39
  It achieves the following results on the evaluation set:
40
+ - Loss: 3.6305
41
+ - Accuracy: 0.0831
42
+ - F1: 0.0049
43
 
44
  ## Model description
45
 
 
58
  ### Training hyperparameters
59
 
60
  The following hyperparameters were used during training:
61
+ - learning_rate: 0.0003
62
  - train_batch_size: 240
63
  - eval_batch_size: 240
64
  - seed: 42
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
+ | 3.3972 | 1.0 | 213 | 3.6305 | 0.0831 | 0.0049 |
74
+ | 3.3928 | 2.0 | 426 | 3.7042 | 0.0815 | 0.0049 |
75
+ | 3.3919 | 3.0 | 639 | 3.7246 | 0.0042 | 0.0003 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2be0e5d2b93528e3c2d787eee86f649e65052a5754f68f6bb7eef6af9b031f46
3
  size 378332188
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3cccc9278c7dc82b49c471f9027263ae2a6d44efa7e63af714f60fced7cba48
3
  size 378332188
runs/Nov24_14-28-16_0e7bc815b640/events.out.tfevents.1732458503.0e7bc815b640.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87eab584cd324d70f64cd40b9ce9ad1391916566e0152bdd17494fdc6e6b7d0f
3
+ size 22622
runs/Nov24_14-28-16_0e7bc815b640/events.out.tfevents.1732459998.0e7bc815b640.30.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51234bbaffa688feacefab14d7fd8438b857981b9544a9cf884418f72a266477
3
+ size 457
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e04f28f3c88691f18d55c1573c355c1e90c1e6b1cf7e0b74110c7a23acf3ad5d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22aa6a6ef3ccee04b900529d8e9dd7cf9d9a5768ccf1a73a796882a030b6e651
3
  size 5176