Commit
•
c159437
1
Parent(s):
024a95e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-8
|
| 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-8
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [jiobiala24/wav2vec2-base-checkpoint-7.1](https://huggingface.co/jiobiala24/wav2vec2-base-checkpoint-7.1) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.9561
|
| 20 |
+
- Wer: 0.3271
|
| 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 |
+
| 0.3117 | 1.59 | 1000 | 0.5514 | 0.3451 |
|
| 54 |
+
| 0.2509 | 3.19 | 2000 | 0.5912 | 0.3328 |
|
| 55 |
+
| 0.1918 | 4.78 | 3000 | 0.6103 | 0.3346 |
|
| 56 |
+
| 0.1612 | 6.38 | 4000 | 0.6469 | 0.3377 |
|
| 57 |
+
| 0.1388 | 7.97 | 5000 | 0.6597 | 0.3391 |
|
| 58 |
+
| 0.121 | 9.57 | 6000 | 0.6911 | 0.3472 |
|
| 59 |
+
| 0.1096 | 11.16 | 7000 | 0.7300 | 0.3457 |
|
| 60 |
+
| 0.0959 | 12.76 | 8000 | 0.7660 | 0.3400 |
|
| 61 |
+
| 0.0882 | 14.35 | 9000 | 0.8316 | 0.3394 |
|
| 62 |
+
| 0.0816 | 15.95 | 10000 | 0.8042 | 0.3357 |
|
| 63 |
+
| 0.0739 | 17.54 | 11000 | 0.8087 | 0.3346 |
|
| 64 |
+
| 0.0717 | 19.14 | 12000 | 0.8590 | 0.3353 |
|
| 65 |
+
| 0.066 | 20.73 | 13000 | 0.8750 | 0.3336 |
|
| 66 |
+
| 0.0629 | 22.33 | 14000 | 0.8759 | 0.3333 |
|
| 67 |
+
| 0.0568 | 23.92 | 15000 | 0.8963 | 0.3321 |
|
| 68 |
+
| 0.0535 | 25.52 | 16000 | 0.9391 | 0.3323 |
|
| 69 |
+
| 0.0509 | 27.11 | 17000 | 0.9279 | 0.3296 |
|
| 70 |
+
| 0.0498 | 28.71 | 18000 | 0.9561 | 0.3271 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.11.3
|
| 76 |
+
- Pytorch 1.10.0+cu111
|
| 77 |
+
- Datasets 1.13.3
|
| 78 |
+
- Tokenizers 0.10.3
|