End of training
Browse files- README.md +34 -11
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Wer
|
| 24 |
type: wer
|
| 25 |
-
value: 0.
|
| 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/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Wer: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -53,23 +53,46 @@ More information needed
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 0.0003
|
| 56 |
-
- train_batch_size:
|
| 57 |
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
| 59 |
- gradient_accumulation_steps: 2
|
| 60 |
-
- total_train_batch_size:
|
| 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:
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
-
| Training Loss | Epoch | Step
|
| 69 |
-
|
| 70 |
-
|
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Wer
|
| 24 |
type: wer
|
| 25 |
+
value: 0.17522160918337998
|
| 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/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.1873
|
| 36 |
+
- Wer: 0.1752
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 0.0003
|
| 56 |
+
- train_batch_size: 8
|
| 57 |
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
| 59 |
- gradient_accumulation_steps: 2
|
| 60 |
+
- total_train_batch_size: 16
|
| 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: 20
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 70 |
+
| 2.5827 | 0.76 | 600 | 0.3985 | 0.5778 |
|
| 71 |
+
| 0.2963 | 1.51 | 1200 | 0.2492 | 0.4142 |
|
| 72 |
+
| 0.2122 | 2.27 | 1800 | 0.2132 | 0.3133 |
|
| 73 |
+
| 0.1686 | 3.03 | 2400 | 0.2078 | 0.2851 |
|
| 74 |
+
| 0.1373 | 3.79 | 3000 | 0.1910 | 0.2750 |
|
| 75 |
+
| 0.1254 | 4.54 | 3600 | 0.1850 | 0.2619 |
|
| 76 |
+
| 0.1137 | 5.3 | 4200 | 0.1874 | 0.2503 |
|
| 77 |
+
| 0.1008 | 6.06 | 4800 | 0.1857 | 0.2554 |
|
| 78 |
+
| 0.0934 | 6.81 | 5400 | 0.1844 | 0.2404 |
|
| 79 |
+
| 0.0876 | 7.57 | 6000 | 0.2001 | 0.2375 |
|
| 80 |
+
| 0.0801 | 8.33 | 6600 | 0.2036 | 0.2512 |
|
| 81 |
+
| 0.0732 | 9.09 | 7200 | 0.1921 | 0.2301 |
|
| 82 |
+
| 0.069 | 9.84 | 7800 | 0.1821 | 0.2330 |
|
| 83 |
+
| 0.0628 | 10.6 | 8400 | 0.1915 | 0.2249 |
|
| 84 |
+
| 0.0619 | 11.36 | 9000 | 0.1881 | 0.2113 |
|
| 85 |
+
| 0.0549 | 12.11 | 9600 | 0.1920 | 0.2076 |
|
| 86 |
+
| 0.0524 | 12.87 | 10200 | 0.1901 | 0.2079 |
|
| 87 |
+
| 0.0492 | 13.63 | 10800 | 0.1767 | 0.2020 |
|
| 88 |
+
| 0.0445 | 14.38 | 11400 | 0.1852 | 0.1933 |
|
| 89 |
+
| 0.0427 | 15.14 | 12000 | 0.1995 | 0.1994 |
|
| 90 |
+
| 0.0398 | 15.9 | 12600 | 0.1922 | 0.1932 |
|
| 91 |
+
| 0.037 | 16.66 | 13200 | 0.1956 | 0.1920 |
|
| 92 |
+
| 0.0353 | 17.41 | 13800 | 0.1990 | 0.1909 |
|
| 93 |
+
| 0.0327 | 18.17 | 14400 | 0.1906 | 0.1784 |
|
| 94 |
+
| 0.0311 | 18.93 | 15000 | 0.1847 | 0.1765 |
|
| 95 |
+
| 0.0295 | 19.68 | 15600 | 0.1873 | 0.1752 |
|
| 96 |
|
| 97 |
|
| 98 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262037165
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e160fcbe1d0aeafd0e6896b94e52462a474068c14933e5511f4e223281d39f7f
|
| 3 |
size 1262037165
|