Commit ·
5c89362
1
Parent(s): c92fa72
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 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-base-checkpoint-13
|
| 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 |
+
# wav2vec2-base-checkpoint-13
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [jiobiala24/wav2vec2-base-checkpoint-12](https://huggingface.co/jiobiala24/wav2vec2-base-checkpoint-12) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.1804
|
| 20 |
+
- Wer: 0.3809
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 32
|
| 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: 1000
|
| 46 |
+
- num_epochs: 30
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 0.2688 | 1.92 | 1000 | 0.6518 | 0.3692 |
|
| 54 |
+
| 0.1944 | 3.85 | 2000 | 0.7188 | 0.3808 |
|
| 55 |
+
| 0.1503 | 5.77 | 3000 | 0.7552 | 0.3853 |
|
| 56 |
+
| 0.1218 | 7.69 | 4000 | 0.8155 | 0.3834 |
|
| 57 |
+
| 0.1024 | 9.62 | 5000 | 0.8867 | 0.3779 |
|
| 58 |
+
| 0.0874 | 11.54 | 6000 | 0.8917 | 0.3866 |
|
| 59 |
+
| 0.0775 | 13.46 | 7000 | 1.0320 | 0.4019 |
|
| 60 |
+
| 0.0712 | 15.38 | 8000 | 1.0110 | 0.3922 |
|
| 61 |
+
| 0.0656 | 17.31 | 9000 | 1.0494 | 0.3885 |
|
| 62 |
+
| 0.0578 | 19.23 | 10000 | 1.1054 | 0.3883 |
|
| 63 |
+
| 0.053 | 21.15 | 11000 | 1.1285 | 0.3938 |
|
| 64 |
+
| 0.0496 | 23.08 | 12000 | 1.1358 | 0.3884 |
|
| 65 |
+
| 0.0459 | 25.0 | 13000 | 1.2062 | 0.3904 |
|
| 66 |
+
| 0.0445 | 26.92 | 14000 | 1.1811 | 0.3830 |
|
| 67 |
+
| 0.0414 | 28.85 | 15000 | 1.1804 | 0.3809 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.11.3
|
| 73 |
+
- Pytorch 1.10.0+cu111
|
| 74 |
+
- Datasets 1.13.3
|
| 75 |
+
- Tokenizers 0.10.3
|