MelanieKoe
commited on
Commit
•
e96341a
1
Parent(s):
bec21d8
Model save
Browse files- README.md +20 -34
- model.safetensors +1 -1
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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:
|
21 |
-
- Wer:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,42 +43,28 @@ The following hyperparameters were used during training:
|
|
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:
|
47 |
-
-
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
53 |
-
|
54 |
-
|
|
55 |
-
| 3.
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
| 3.2089 | 107.14 | 1500 | 3.3278 | 1.0 |
|
69 |
-
| 3.2095 | 114.29 | 1600 | 3.3363 | 1.0 |
|
70 |
-
| 3.2053 | 121.43 | 1700 | 3.3086 | 1.0 |
|
71 |
-
| 3.2009 | 128.57 | 1800 | 3.3105 | 1.0 |
|
72 |
-
| 3.2037 | 135.71 | 1900 | 3.3275 | 1.0 |
|
73 |
-
| 3.2074 | 142.86 | 2000 | 3.3092 | 1.0 |
|
74 |
-
| 3.2134 | 150.0 | 2100 | 3.3099 | 1.0 |
|
75 |
-
| 3.2042 | 157.14 | 2200 | 3.3025 | 1.0 |
|
76 |
-
| 3.2006 | 164.29 | 2300 | 3.3110 | 1.0 |
|
77 |
-
| 3.2052 | 171.43 | 2400 | 3.3393 | 1.0 |
|
78 |
-
| 3.2052 | 178.57 | 2500 | 3.3191 | 1.0 |
|
79 |
-
| 3.2026 | 185.71 | 2600 | 3.3303 | 1.0 |
|
80 |
-
| 3.2113 | 192.86 | 2700 | 3.3261 | 1.0 |
|
81 |
-
| 3.2048 | 200.0 | 2800 | 3.3227 | 1.0 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
|
|
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: 2.2956
|
21 |
+
- Wer: 0.1811
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
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: 1000
|
47 |
+
- training_steps: 3500
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
54 |
+
| 21.7228 | 17.86 | 250 | 3.7139 | 1.0 |
|
55 |
+
| 3.1757 | 35.71 | 500 | 3.1149 | 1.0 |
|
56 |
+
| 2.8079 | 53.57 | 750 | 1.7093 | 1.0038 |
|
57 |
+
| 0.301 | 71.43 | 1000 | 1.4764 | 0.2443 |
|
58 |
+
| 0.0637 | 89.29 | 1250 | 1.7091 | 0.2200 |
|
59 |
+
| 0.0311 | 107.14 | 1500 | 1.7022 | 0.2055 |
|
60 |
+
| 0.021 | 125.0 | 1750 | 2.0876 | 0.2016 |
|
61 |
+
| 0.0154 | 142.86 | 2000 | 2.2718 | 0.1974 |
|
62 |
+
| 0.0114 | 160.71 | 2250 | 2.1541 | 0.1845 |
|
63 |
+
| 0.0089 | 178.57 | 2500 | 2.2868 | 0.1854 |
|
64 |
+
| 0.0074 | 196.43 | 2750 | 2.3831 | 0.1914 |
|
65 |
+
| 0.0062 | 214.29 | 3000 | 2.2381 | 0.1841 |
|
66 |
+
| 0.0054 | 232.14 | 3250 | 2.4147 | 0.1824 |
|
67 |
+
| 0.0056 | 250.0 | 3500 | 2.2956 | 0.1811 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
|
70 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377629528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f2a1ec108b95c1e87d1a43e7c98391129d78a8e44ab675eefdbd3be89e4943b
|
3 |
size 377629528
|