update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: ctrlv-speechrecognition-model
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# ctrlv-speechrecognition-model
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4730
|
| 18 |
+
- Wer: 0.3031
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 1000
|
| 44 |
+
- num_epochs: 60
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 51 |
+
| 3.53 | 3.45 | 500 | 1.4021 | 0.9307 |
|
| 52 |
+
| 0.6077 | 6.9 | 1000 | 0.4255 | 0.4353 |
|
| 53 |
+
| 0.2331 | 10.34 | 1500 | 0.3887 | 0.3650 |
|
| 54 |
+
| 0.1436 | 13.79 | 2000 | 0.3579 | 0.3393 |
|
| 55 |
+
| 0.1021 | 17.24 | 2500 | 0.4447 | 0.3440 |
|
| 56 |
+
| 0.0797 | 20.69 | 3000 | 0.4041 | 0.3291 |
|
| 57 |
+
| 0.0657 | 24.14 | 3500 | 0.4262 | 0.3368 |
|
| 58 |
+
| 0.0525 | 27.59 | 4000 | 0.4937 | 0.3429 |
|
| 59 |
+
| 0.0454 | 31.03 | 4500 | 0.4449 | 0.3244 |
|
| 60 |
+
| 0.0373 | 34.48 | 5000 | 0.4363 | 0.3288 |
|
| 61 |
+
| 0.0321 | 37.93 | 5500 | 0.4519 | 0.3204 |
|
| 62 |
+
| 0.0288 | 41.38 | 6000 | 0.4440 | 0.3145 |
|
| 63 |
+
| 0.0259 | 44.83 | 6500 | 0.4691 | 0.3182 |
|
| 64 |
+
| 0.0203 | 48.28 | 7000 | 0.5062 | 0.3162 |
|
| 65 |
+
| 0.0171 | 51.72 | 7500 | 0.4762 | 0.3129 |
|
| 66 |
+
| 0.0166 | 55.17 | 8000 | 0.4772 | 0.3090 |
|
| 67 |
+
| 0.0147 | 58.62 | 8500 | 0.4730 | 0.3031 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.11.3
|
| 73 |
+
- Pytorch 1.10.0+cu111
|
| 74 |
+
- Datasets 1.18.3
|
| 75 |
+
- Tokenizers 0.10.3
|