Commit
•
7db016f
1
Parent(s):
e9ae8d5
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vec2-xlsr-53-ft-btb-cv-cy-cand
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# wav2vec2-xlsr-53-ft-btb-cv-cy-cand
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: inf
|
| 21 |
+
- Wer: 0.3598
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0003
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 800
|
| 47 |
+
- training_steps: 8000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 54 |
+
| 4.6973 | 0.0714 | 500 | inf | 1.0 |
|
| 55 |
+
| 1.448 | 0.1428 | 1000 | inf | 0.7574 |
|
| 56 |
+
| 1.053 | 0.2142 | 1500 | inf | 0.6584 |
|
| 57 |
+
| 0.9304 | 0.2856 | 2000 | inf | 0.5963 |
|
| 58 |
+
| 0.8755 | 0.3569 | 2500 | inf | 0.5946 |
|
| 59 |
+
| 0.8238 | 0.4283 | 3000 | inf | 0.5392 |
|
| 60 |
+
| 0.7819 | 0.4997 | 3500 | inf | 0.4967 |
|
| 61 |
+
| 0.729 | 0.5711 | 4000 | inf | 0.4834 |
|
| 62 |
+
| 0.6923 | 0.6425 | 4500 | inf | 0.4564 |
|
| 63 |
+
| 0.7052 | 0.7139 | 5000 | inf | 0.4346 |
|
| 64 |
+
| 0.6675 | 0.7853 | 5500 | inf | 0.4163 |
|
| 65 |
+
| 0.6217 | 0.8567 | 6000 | inf | 0.3962 |
|
| 66 |
+
| 0.5954 | 0.9280 | 6500 | inf | 0.3883 |
|
| 67 |
+
| 0.5687 | 0.9994 | 7000 | inf | 0.3746 |
|
| 68 |
+
| 0.477 | 1.0708 | 7500 | inf | 0.3647 |
|
| 69 |
+
| 0.4804 | 1.1422 | 8000 | inf | 0.3598 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.44.0
|
| 75 |
+
- Pytorch 2.4.0+cu121
|
| 76 |
+
- Datasets 2.21.0
|
| 77 |
+
- Tokenizers 0.19.1
|