update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: hubert-base-libri-demo-feature_extractor_not_frozen_v3_25epochs_check
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# hubert-base-libri-demo-feature_extractor_not_frozen_v3_25epochs_check
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1231
|
| 20 |
+
- Wer: 0.1112
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.00015
|
| 40 |
+
- train_batch_size: 64
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 3000
|
| 46 |
+
- num_epochs: 25
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 4.3342 | 1.12 | 500 | 3.4935 | 1.0000 |
|
| 54 |
+
| 2.8802 | 2.24 | 1000 | 3.5637 | 1.0000 |
|
| 55 |
+
| 2.1866 | 3.36 | 1500 | 0.7219 | 0.6232 |
|
| 56 |
+
| 0.6141 | 4.48 | 2000 | 0.2954 | 0.3238 |
|
| 57 |
+
| 0.3328 | 5.61 | 2500 | 0.1810 | 0.2212 |
|
| 58 |
+
| 0.2251 | 6.73 | 3000 | 0.1377 | 0.1640 |
|
| 59 |
+
| 0.1861 | 7.85 | 3500 | 0.1270 | 0.1473 |
|
| 60 |
+
| 0.1671 | 8.97 | 4000 | 0.1173 | 0.1372 |
|
| 61 |
+
| 0.1496 | 10.09 | 4500 | 0.1218 | 0.1322 |
|
| 62 |
+
| 0.117 | 11.21 | 5000 | 0.1180 | 0.1268 |
|
| 63 |
+
| 0.1182 | 12.33 | 5500 | 0.1255 | 0.1257 |
|
| 64 |
+
| 0.0948 | 13.45 | 6000 | 0.1215 | 0.1221 |
|
| 65 |
+
| 0.0935 | 14.57 | 6500 | 0.1233 | 0.1217 |
|
| 66 |
+
| 0.0873 | 15.7 | 7000 | 0.1124 | 0.1209 |
|
| 67 |
+
| 0.0798 | 16.82 | 7500 | 0.1172 | 0.1185 |
|
| 68 |
+
| 0.0752 | 17.94 | 8000 | 0.1197 | 0.1171 |
|
| 69 |
+
| 0.0747 | 19.06 | 8500 | 0.1252 | 0.1171 |
|
| 70 |
+
| 0.0775 | 20.18 | 9000 | 0.1209 | 0.1149 |
|
| 71 |
+
| 0.0665 | 21.3 | 9500 | 0.1180 | 0.1133 |
|
| 72 |
+
| 0.0657 | 22.42 | 10000 | 0.1240 | 0.1122 |
|
| 73 |
+
| 0.0606 | 23.54 | 10500 | 0.1222 | 0.1110 |
|
| 74 |
+
| 0.0581 | 24.66 | 11000 | 0.1231 | 0.1112 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.30.0.dev0
|
| 80 |
+
- Pytorch 2.0.1
|
| 81 |
+
- Datasets 2.12.1.dev0
|
| 82 |
+
- Tokenizers 0.13.3
|