Commit
•
ca850d6
1
Parent(s):
c681913
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-cv-10000
|
| 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-cv-10000
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [jiobiala24/wav2vec2-base-cv](https://huggingface.co/jiobiala24/wav2vec2-base-cv) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3393
|
| 20 |
+
- Wer: 0.3684
|
| 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: 8
|
| 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 |
+
| 0.4243 | 1.6 | 1000 | 0.7742 | 0.4210 |
|
| 54 |
+
| 0.3636 | 3.2 | 2000 | 0.8621 | 0.4229 |
|
| 55 |
+
| 0.2638 | 4.8 | 3000 | 0.9328 | 0.4094 |
|
| 56 |
+
| 0.2273 | 6.4 | 4000 | 0.9556 | 0.4087 |
|
| 57 |
+
| 0.187 | 8.0 | 5000 | 0.9093 | 0.4019 |
|
| 58 |
+
| 0.1593 | 9.6 | 6000 | 0.9842 | 0.4029 |
|
| 59 |
+
| 0.1362 | 11.2 | 7000 | 1.0651 | 0.4077 |
|
| 60 |
+
| 0.1125 | 12.8 | 8000 | 1.0550 | 0.3959 |
|
| 61 |
+
| 0.103 | 14.4 | 9000 | 1.1919 | 0.4002 |
|
| 62 |
+
| 0.0948 | 16.0 | 10000 | 1.1901 | 0.3983 |
|
| 63 |
+
| 0.0791 | 17.6 | 11000 | 1.1091 | 0.3860 |
|
| 64 |
+
| 0.0703 | 19.2 | 12000 | 1.2823 | 0.3904 |
|
| 65 |
+
| 0.0641 | 20.8 | 13000 | 1.2625 | 0.3817 |
|
| 66 |
+
| 0.057 | 22.4 | 14000 | 1.2821 | 0.3776 |
|
| 67 |
+
| 0.0546 | 24.0 | 15000 | 1.2975 | 0.3770 |
|
| 68 |
+
| 0.0457 | 25.6 | 16000 | 1.2998 | 0.3714 |
|
| 69 |
+
| 0.0433 | 27.2 | 17000 | 1.3574 | 0.3721 |
|
| 70 |
+
| 0.0423 | 28.8 | 18000 | 1.3393 | 0.3684 |
|
| 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
|