Hugging Face's logo

Zelyanoth
/
wav2vec2-bert-fon

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Zelyanoth commited on
Commit
e03fccb
•
1 Parent(s): 30b2462

End of training

Browse files
Files changed (3) hide show
  1. README.md +32 -32
  2. model.safetensors +1 -1
  3. runs/Jun20_23-33-44_05e8c5fb976b/events.out.tfevents.1718926633.05e8c5fb976b.24.0 +2 -2
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/w2v-bert-2.0
6
  datasets:
7
  - generator
8
  metrics:
@@ -11,8 +11,8 @@ model-index:
11
  - name: wav2vec2-bert-fon
12
  results:
13
  - task:
14
- type: automatic-speech-recognition
15
  name: Automatic Speech Recognition
 
16
  dataset:
17
  name: generator
18
  type: generator
@@ -20,9 +20,9 @@ model-index:
20
  split: train
21
  args: default
22
  metrics:
23
- - type: wer
24
- value: 0.2183013319494897
25
- name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the generator dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.2480
36
- - Wer: 0.2183
37
 
38
  ## Model description
39
 
@@ -61,35 +61,35 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - num_epochs: 8
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer |
70
- |:-------------:|:-----:|:-----:|:---------------:|:------:|
71
- | 1.7256 | 0.35 | 500 | 0.7130 | 0.5735 |
72
- | 0.497 | 0.7 | 1000 | 0.4485 | 0.4113 |
73
- | 0.4133 | 1.05 | 1500 | 0.3067 | 0.2729 |
74
- | 0.303 | 1.4 | 2000 | 0.2747 | 0.2340 |
75
- | 0.2556 | 1.75 | 2500 | 0.2047 | 0.1793 |
76
- | 0.2378 | 2.1 | 3000 | 0.1794 | 0.1528 |
77
- | 0.1619 | 2.45 | 3500 | 0.1831 | 0.1526 |
78
- | 0.1702 | 2.8 | 4000 | 0.1707 | 0.1275 |
79
- | 0.142 | 3.15 | 4500 | 0.1653 | 0.1273 |
80
- | 0.133 | 3.5 | 5000 | 0.1467 | 0.1218 |
81
- | 0.1864 | 3.85 | 5500 | 0.2228 | 0.1565 |
82
- | 0.3031 | 4.21 | 6000 | 0.2462 | 0.2076 |
83
- | 0.3263 | 4.56 | 6500 | 0.2432 | 0.1713 |
84
- | 0.3354 | 4.91 | 7000 | 0.2506 | 0.2277 |
85
- | 0.3266 | 5.26 | 7500 | 0.2480 | 0.2183 |
86
- | 0.3247 | 5.61 | 8000 | 0.2480 | 0.2183 |
87
- | 0.3416 | 5.96 | 8500 | 0.2480 | 0.2183 |
88
- | 0.323 | 6.31 | 9000 | 0.2480 | 0.2183 |
89
- | 0.3303 | 6.66 | 9500 | 0.2480 | 0.2183 |
90
- | 0.3328 | 7.01 | 10000 | 0.2480 | 0.2183 |
91
- | 0.3244 | 7.36 | 10500 | 0.2480 | 0.2183 |
92
- | 0.3362 | 7.71 | 11000 | 0.2480 | 0.2183 |
93
 
94
 
95
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: facebook/w2v-bert-2.0
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - generator
8
  metrics:
 
11
  - name: wav2vec2-bert-fon
12
  results:
13
  - task:
 
14
  name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
  dataset:
17
  name: generator
18
  type: generator
 
20
  split: train
21
  args: default
22
  metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.17488323819408408
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the generator dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2409
36
+ - Wer: 0.1749
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 4
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
71
+ | No log | 0.18 | 250 | 1.2212 | 0.8079 |
72
+ | 2.1756 | 0.35 | 500 | 0.6697 | 0.6058 |
73
+ | 2.1756 | 0.53 | 750 | 0.5137 | 0.4606 |
74
+ | 0.5041 | 0.7 | 1000 | 0.4337 | 0.4234 |
75
+ | 0.5041 | 0.88 | 1250 | 0.3452 | 0.3529 |
76
+ | 0.426 | 1.05 | 1500 | 0.2770 | 0.2910 |
77
+ | 0.426 | 1.23 | 1750 | 0.2681 | 0.2439 |
78
+ | 0.2916 | 1.4 | 2000 | 0.2423 | 0.2155 |
79
+ | 0.2916 | 1.58 | 2250 | 0.2342 | 0.2077 |
80
+ | 0.2591 | 1.75 | 2500 | 0.1986 | 0.1791 |
81
+ | 0.2591 | 1.93 | 2750 | 0.1864 | 0.1597 |
82
+ | 0.2261 | 2.1 | 3000 | 0.1712 | 0.1419 |
83
+ | 0.2261 | 2.28 | 3250 | 0.1786 | 0.1497 |
84
+ | 0.1564 | 2.45 | 3500 | 0.1612 | 0.1324 |
85
+ | 0.1564 | 2.63 | 3750 | 0.1730 | 0.1591 |
86
+ | 0.1542 | 2.8 | 4000 | 0.1558 | 0.1364 |
87
+ | 0.1542 | 2.98 | 4250 | 0.1493 | 0.1581 |
88
+ | 0.1559 | 3.15 | 4500 | 0.1489 | 0.1347 |
89
+ | 0.1559 | 3.33 | 4750 | 0.2036 | 0.1486 |
90
+ | 0.1992 | 3.5 | 5000 | 0.2644 | 0.1582 |
91
+ | 0.1992 | 3.68 | 5250 | 0.2401 | 0.1878 |
92
+ | 0.291 | 3.85 | 5500 | 0.2409 | 0.1749 |
93
 
94
 
95
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72854484af5c5e8ada90def3b1e4b5a6b59fd0597fe2f8428b3593183bfc1976
3
  size 2422970360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d32c1feda413314b0cb425ff413009d8a4e754417c001a8b7317104ebebd5b
3
  size 2422970360
runs/Jun20_23-33-44_05e8c5fb976b/events.out.tfevents.1718926633.05e8c5fb976b.24.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1418572e1c2e7f51cb7132b658d26acd76abb07320f97997f014b8f0ca34b26
3
- size 15191
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb2ccafcc76e8d56d359c26b221d4d03f63ae5d3d7753c26b4a723fc6bbae61
3
+ size 15545