Commit
•
d0613e2
1
Parent(s):
73ee645
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- audiofolder
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: xls-r-fleurs_nl-run3
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: audiofolder
|
| 17 |
+
type: audiofolder
|
| 18 |
+
config: default
|
| 19 |
+
split: validation
|
| 20 |
+
args: default
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 0.42659804983748645
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# xls-r-fleurs_nl-run3
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the audiofolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.5523
|
| 35 |
+
- Wer: 0.4266
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 0.0003
|
| 55 |
+
- train_batch_size: 4
|
| 56 |
+
- eval_batch_size: 4
|
| 57 |
+
- seed: 42
|
| 58 |
+
- gradient_accumulation_steps: 3
|
| 59 |
+
- total_train_batch_size: 12
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_steps: 500
|
| 63 |
+
- num_epochs: 30
|
| 64 |
+
- mixed_precision_training: Native AMP
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 70 |
+
| 7.768 | 0.41 | 100 | 3.9649 | 1.0 |
|
| 71 |
+
| 3.2646 | 0.82 | 200 | 2.9551 | 1.0 |
|
| 72 |
+
| 2.9217 | 1.23 | 300 | 2.9128 | 1.0 |
|
| 73 |
+
| 2.9064 | 1.64 | 400 | 2.9067 | 1.0 |
|
| 74 |
+
| 2.6775 | 2.05 | 500 | 1.5774 | 0.9177 |
|
| 75 |
+
| 1.1026 | 2.47 | 600 | 0.8813 | 0.7216 |
|
| 76 |
+
| 0.6905 | 2.88 | 700 | 0.7287 | 0.6138 |
|
| 77 |
+
| 0.4936 | 3.29 | 800 | 0.6156 | 0.5439 |
|
| 78 |
+
| 0.3837 | 3.7 | 900 | 0.5608 | 0.4992 |
|
| 79 |
+
| 0.3176 | 4.11 | 1000 | 0.5326 | 0.4542 |
|
| 80 |
+
| 0.2391 | 4.52 | 1100 | 0.5221 | 0.4466 |
|
| 81 |
+
| 0.2426 | 4.93 | 1200 | 0.5127 | 0.4328 |
|
| 82 |
+
| 0.1882 | 5.34 | 1300 | 0.5311 | 0.4247 |
|
| 83 |
+
| 0.1718 | 5.75 | 1400 | 0.5523 | 0.4266 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.28.0
|
| 89 |
+
- Pytorch 2.0.1+cu117
|
| 90 |
+
- Datasets 2.14.4
|
| 91 |
+
- Tokenizers 0.13.3
|