Commit
•
e2ae8fd
1
Parent(s):
920a2c8
Model save
Browse files
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
5 |
-
- automatic-speech-recognition
|
6 |
-
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
|
7 |
- generated_from_trainer
|
8 |
metrics:
|
9 |
- wer
|
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# wav2vec2-xlsr-53-ft-btb-ccv-cy
|
19 |
|
20 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss:
|
23 |
-
- Wer: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -40,39 +38,49 @@ More information needed
|
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 0.0003
|
43 |
-
- train_batch_size:
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_steps: 500
|
49 |
-
- training_steps:
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
56 |
-
| No log | 0.
|
57 |
-
| No log | 0.
|
58 |
-
| No log | 0.
|
59 |
-
| No log |
|
60 |
-
| 3.
|
61 |
-
| 3.
|
62 |
-
| 3.
|
63 |
-
| 3.
|
64 |
-
| 3.
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- wer
|
|
|
15 |
|
16 |
# wav2vec2-xlsr-53-ft-btb-ccv-cy
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.5355
|
21 |
+
- Wer: 0.4186
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0003
|
41 |
+
- train_batch_size: 8
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 500
|
47 |
+
- training_steps: 3000
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
54 |
+
| No log | 0.0194 | 100 | 3.5494 | 1.0 |
|
55 |
+
| No log | 0.0387 | 200 | 3.0426 | 1.0 |
|
56 |
+
| No log | 0.0581 | 300 | 2.8965 | 1.0 |
|
57 |
+
| No log | 0.0774 | 400 | 1.8263 | 0.9829 |
|
58 |
+
| 3.9715 | 0.0968 | 500 | 1.3860 | 0.8749 |
|
59 |
+
| 3.9715 | 0.1161 | 600 | 1.3084 | 0.8153 |
|
60 |
+
| 3.9715 | 0.1355 | 700 | 1.0550 | 0.7337 |
|
61 |
+
| 3.9715 | 0.1549 | 800 | 1.0012 | 0.7190 |
|
62 |
+
| 3.9715 | 0.1742 | 900 | 0.9137 | 0.6752 |
|
63 |
+
| 1.0155 | 0.1936 | 1000 | 0.8486 | 0.6469 |
|
64 |
+
| 1.0155 | 0.2129 | 1100 | 0.8535 | 0.6112 |
|
65 |
+
| 1.0155 | 0.2323 | 1200 | 0.8350 | 0.6193 |
|
66 |
+
| 1.0155 | 0.2516 | 1300 | 0.7681 | 0.5670 |
|
67 |
+
| 1.0155 | 0.2710 | 1400 | 0.7377 | 0.5559 |
|
68 |
+
| 0.7987 | 0.2904 | 1500 | 0.7130 | 0.5437 |
|
69 |
+
| 0.7987 | 0.3097 | 1600 | 0.7040 | 0.5452 |
|
70 |
+
| 0.7987 | 0.3291 | 1700 | 0.6729 | 0.5051 |
|
71 |
+
| 0.7987 | 0.3484 | 1800 | 0.6646 | 0.5113 |
|
72 |
+
| 0.7987 | 0.3678 | 1900 | 0.6531 | 0.4969 |
|
73 |
+
| 0.6851 | 0.3871 | 2000 | 0.6414 | 0.5038 |
|
74 |
+
| 0.6851 | 0.4065 | 2100 | 0.6109 | 0.4677 |
|
75 |
+
| 0.6851 | 0.4259 | 2200 | 0.6035 | 0.4692 |
|
76 |
+
| 0.6851 | 0.4452 | 2300 | 0.5802 | 0.4590 |
|
77 |
+
| 0.6851 | 0.4646 | 2400 | 0.5720 | 0.4455 |
|
78 |
+
| 0.5979 | 0.4839 | 2500 | 0.5695 | 0.4426 |
|
79 |
+
| 0.5979 | 0.5033 | 2600 | 0.5557 | 0.4351 |
|
80 |
+
| 0.5979 | 0.5226 | 2700 | 0.5499 | 0.4270 |
|
81 |
+
| 0.5979 | 0.5420 | 2800 | 0.5451 | 0.4258 |
|
82 |
+
| 0.5979 | 0.5614 | 2900 | 0.5383 | 0.4217 |
|
83 |
+
| 0.5753 | 0.5807 | 3000 | 0.5355 | 0.4186 |
|
84 |
|
85 |
|
86 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1261996080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aeb49b0928a16f898a62ddba46e8ad9f1530e102bb2cdb5f717098412b28738
|
3 |
size 1261996080
|
runs/May31_06-27-23_af3b5d38d2a2/events.out.tfevents.1717133258.af3b5d38d2a2.810.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cfdabbf4fffe56bd0c0c559fba3a2e44055aecc618181f2413c5f3daa8abcd7
|
3 |
+
size 17590
|