Commit
•
d3139ae
1
Parent(s):
c121a5d
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vec2-btb-cv-ft-btb-cy
|
| 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-btb-cv-ft-btb-cy
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy](https://huggingface.co/DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6057
|
| 21 |
+
- Wer: 0.3738
|
| 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: 16
|
| 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: 300
|
| 47 |
+
- training_steps: 3000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 54 |
+
| No log | 0.1139 | 200 | 0.7394 | 0.4966 |
|
| 55 |
+
| No log | 0.2278 | 400 | 0.6406 | 0.4617 |
|
| 56 |
+
| 2.0443 | 0.3417 | 600 | 0.6105 | 0.4496 |
|
| 57 |
+
| 2.0443 | 0.4556 | 800 | 0.5865 | 0.4414 |
|
| 58 |
+
| 0.7145 | 0.5695 | 1000 | 0.5439 | 0.4165 |
|
| 59 |
+
| 0.7145 | 0.6834 | 1200 | 0.5428 | 0.4172 |
|
| 60 |
+
| 0.7145 | 0.7973 | 1400 | 0.5055 | 0.3872 |
|
| 61 |
+
| 0.6574 | 0.9112 | 1600 | 0.4916 | 0.3803 |
|
| 62 |
+
| 0.6574 | 1.0251 | 1800 | 0.4755 | 0.3658 |
|
| 63 |
+
| 0.577 | 1.1390 | 2000 | 0.4695 | 0.3594 |
|
| 64 |
+
| 0.577 | 1.2528 | 2200 | 0.4656 | 0.3505 |
|
| 65 |
+
| 0.577 | 1.3667 | 2400 | 0.5080 | 0.3547 |
|
| 66 |
+
| 0.534 | 1.4806 | 2600 | 0.5481 | 0.3640 |
|
| 67 |
+
| 0.534 | 1.5945 | 2800 | 0.6369 | 0.3903 |
|
| 68 |
+
| 0.7065 | 1.7084 | 3000 | 0.6057 | 0.3738 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.44.0
|
| 74 |
+
- Pytorch 2.4.0+cu121
|
| 75 |
+
- Datasets 2.21.0
|
| 76 |
+
- Tokenizers 0.19.1
|