End of training
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
base_model: facebook/hubert-large-ls960-ft
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: hubert-large-timit-upsample-decoder
|
| 9 |
results: []
|
|
@@ -16,13 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
- eval_runtime: 163.5833
|
| 22 |
-
- eval_samples_per_second: 8.497
|
| 23 |
-
- eval_steps_per_second: 4.249
|
| 24 |
-
- eval_wer: 0.9181
|
| 25 |
-
- step: 4000
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -53,6 +50,28 @@ The following hyperparameters were used during training:
|
|
| 53 |
- num_epochs: 40
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.51.3
|
|
|
|
| 4 |
base_model: facebook/hubert-large-ls960-ft
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: hubert-large-timit-upsample-decoder
|
| 11 |
results: []
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4975
|
| 22 |
+
- Wer: 0.9749
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 50 |
- num_epochs: 40
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
| 57 |
+
| 83.048 | 2.4752 | 500 | 48.3229 | 0.9459 |
|
| 58 |
+
| 2.1777 | 4.9505 | 1000 | 3.3841 | 0.9775 |
|
| 59 |
+
| 2.5735 | 7.4257 | 1500 | 2.1042 | 0.9698 |
|
| 60 |
+
| 5.3683 | 9.9010 | 2000 | 1.5244 | 0.9699 |
|
| 61 |
+
| 1.906 | 12.3762 | 2500 | 1.3064 | 0.9128 |
|
| 62 |
+
| 1.9468 | 14.8515 | 3000 | 1.3597 | 0.9174 |
|
| 63 |
+
| 1.6598 | 17.3267 | 3500 | 1.1801 | 0.9093 |
|
| 64 |
+
| 1.2808 | 19.8020 | 4000 | 1.6481 | 0.9181 |
|
| 65 |
+
| 2.0953 | 22.2772 | 4500 | 3.1021 | 0.9602 |
|
| 66 |
+
| 0.5282 | 24.7525 | 5000 | 0.5278 | 0.9755 |
|
| 67 |
+
| 7.1607 | 27.2277 | 5500 | 0.9557 | 0.9823 |
|
| 68 |
+
| 4.1975 | 29.7030 | 6000 | 13.0365 | 0.9301 |
|
| 69 |
+
| 0.5248 | 32.1782 | 6500 | 0.5075 | 0.9840 |
|
| 70 |
+
| 0.5065 | 34.6535 | 7000 | 0.5001 | 0.9834 |
|
| 71 |
+
| 0.4997 | 37.1287 | 7500 | 0.5032 | 0.9793 |
|
| 72 |
+
| 0.5072 | 39.6040 | 8000 | 0.4975 | 0.9749 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
- Transformers 4.51.3
|