End of training
Browse files
README.md
CHANGED
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# Osiris_asr_model
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
- Wer: 1.0
|
22 |
|
23 |
## Model description
|
@@ -38,23 +38,41 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 1e-05
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- gradient_accumulation_steps: 2
|
45 |
-
- total_train_batch_size:
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
-
- lr_scheduler_warmup_steps:
|
49 |
-
- training_steps:
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch
|
55 |
-
|
56 |
-
|
|
57 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
15 |
|
16 |
# Osiris_asr_model
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 3.0600
|
21 |
- Wer: 1.0
|
22 |
|
23 |
## Model description
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 10
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 20
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 50
|
49 |
+
- training_steps: 1000
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
56 |
+
| 45.8209 | 50.0 | 50 | 21.0347 | 1.0182 |
|
57 |
+
| 10.2898 | 100.0 | 100 | 5.1552 | 1.0 |
|
58 |
+
| 5.7188 | 150.0 | 150 | 4.9140 | 1.0 |
|
59 |
+
| 5.3358 | 200.0 | 200 | 4.7650 | 1.0 |
|
60 |
+
| 5.1381 | 250.0 | 250 | 4.6797 | 1.0 |
|
61 |
+
| 4.9841 | 300.0 | 300 | 4.6168 | 1.0 |
|
62 |
+
| 4.9255 | 350.0 | 350 | 4.5741 | 1.0 |
|
63 |
+
| 4.8353 | 400.0 | 400 | 4.5321 | 1.0 |
|
64 |
+
| 4.7704 | 450.0 | 450 | 4.5100 | 1.0 |
|
65 |
+
| 4.6257 | 500.0 | 500 | 3.9382 | 1.0 |
|
66 |
+
| 3.8106 | 550.0 | 550 | 3.3939 | 1.0 |
|
67 |
+
| 3.5095 | 600.0 | 600 | 3.2887 | 1.0 |
|
68 |
+
| 3.3716 | 650.0 | 650 | 3.1967 | 1.0 |
|
69 |
+
| 3.3025 | 700.0 | 700 | 3.1539 | 1.0 |
|
70 |
+
| 3.2532 | 750.0 | 750 | 3.1477 | 1.0 |
|
71 |
+
| 3.2086 | 800.0 | 800 | 3.0984 | 1.0 |
|
72 |
+
| 3.1889 | 850.0 | 850 | 3.0857 | 1.0 |
|
73 |
+
| 3.162 | 900.0 | 900 | 3.0819 | 1.0 |
|
74 |
+
| 3.1411 | 950.0 | 950 | 3.0610 | 1.0 |
|
75 |
+
| 3.1397 | 1000.0 | 1000 | 3.0600 | 1.0 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377611120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0340c321c7a82ab1d5aaa8344957dedea0696755dae89b3c504256b3bf3dea1
|
3 |
size 377611120
|
runs/Jan02_18-43-57_5347c18ae0ee/events.out.tfevents.1704221040.5347c18ae0ee.857.1
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:e2d05d3e9d920c3927b1cdfc5d6311b3fa3f89d4fecf3b5f2904d0ce6c0c02ed
|
3 |
+
size 15775
|