Commit
·
ff86643
1
Parent(s):
e1a6b69
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec_mle
|
| 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 |
+
# wav2vec_mle
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 4.3076
|
| 18 |
+
- Wer: 1.0
|
| 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: 0.0003
|
| 38 |
+
- train_batch_size: 6
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 12
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 20
|
| 46 |
+
- num_epochs: 60
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 52 |
+
| 7.3604 | 3.33 | 30 | 4.4612 | 1.0 |
|
| 53 |
+
| 4.502 | 6.67 | 60 | 4.5906 | 1.0 |
|
| 54 |
+
| 4.2842 | 10.0 | 90 | 4.4217 | 1.0 |
|
| 55 |
+
| 4.3833 | 13.33 | 120 | 4.3967 | 1.0 |
|
| 56 |
+
| 4.2631 | 16.67 | 150 | 4.3469 | 1.0 |
|
| 57 |
+
| 4.3357 | 20.0 | 180 | 4.3372 | 1.0 |
|
| 58 |
+
| 4.3941 | 23.33 | 210 | 4.3187 | 1.0 |
|
| 59 |
+
| 4.393 | 26.67 | 240 | 4.2981 | 1.0 |
|
| 60 |
+
| 4.3619 | 30.0 | 270 | 4.3049 | 1.0 |
|
| 61 |
+
| 4.3849 | 33.33 | 300 | 4.3138 | 1.0 |
|
| 62 |
+
| 4.3186 | 36.67 | 330 | 4.3123 | 1.0 |
|
| 63 |
+
| 4.3196 | 40.0 | 360 | 4.3097 | 1.0 |
|
| 64 |
+
| 4.3212 | 43.33 | 390 | 4.3279 | 1.0 |
|
| 65 |
+
| 4.3108 | 46.67 | 420 | 4.3249 | 1.0 |
|
| 66 |
+
| 4.3112 | 50.0 | 450 | 4.3093 | 1.0 |
|
| 67 |
+
| 4.2994 | 53.33 | 480 | 4.3198 | 1.0 |
|
| 68 |
+
| 4.2958 | 56.67 | 510 | 4.3071 | 1.0 |
|
| 69 |
+
| 4.2905 | 60.0 | 540 | 4.3076 | 1.0 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.17.0
|
| 75 |
+
- Pytorch 1.11.0+cu113
|
| 76 |
+
- Datasets 1.18.3
|
| 77 |
+
- Tokenizers 0.12.1
|