Commit
•
03de0f3
1
Parent(s):
53a8894
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- el
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- mozilla-foundation/common_voice_7_0
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- common_voice
|
| 11 |
+
model-index:
|
| 12 |
+
- name: wav2vec2-large-xls-r-300m-greek
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# wav2vec2-large-xls-r-300m-greek
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - EL dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.6831
|
| 24 |
+
- Wer: 0.4287
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0003
|
| 44 |
+
- train_batch_size: 32
|
| 45 |
+
- eval_batch_size: 32
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 100.0
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 57 |
+
| 3.0798 | 4.42 | 500 | 3.0010 | 1.0012 |
|
| 58 |
+
| 1.4336 | 8.85 | 1000 | 0.8481 | 0.6911 |
|
| 59 |
+
| 1.2062 | 13.27 | 1500 | 0.7312 | 0.6333 |
|
| 60 |
+
| 1.0481 | 17.7 | 2000 | 0.6850 | 0.5359 |
|
| 61 |
+
| 0.9837 | 22.12 | 2500 | 0.6337 | 0.5316 |
|
| 62 |
+
| 0.9108 | 26.55 | 3000 | 0.6258 | 0.5079 |
|
| 63 |
+
| 0.8439 | 30.97 | 3500 | 0.6301 | 0.4888 |
|
| 64 |
+
| 0.7901 | 35.4 | 4000 | 0.6245 | 0.4977 |
|
| 65 |
+
| 0.7669 | 39.82 | 4500 | 0.6164 | 0.4672 |
|
| 66 |
+
| 0.7196 | 44.25 | 5000 | 0.6039 | 0.4688 |
|
| 67 |
+
| 0.6715 | 48.67 | 5500 | 0.5900 | 0.4573 |
|
| 68 |
+
| 0.6441 | 53.1 | 6000 | 0.7002 | 0.4798 |
|
| 69 |
+
| 0.5938 | 57.52 | 6500 | 0.6249 | 0.4579 |
|
| 70 |
+
| 0.5541 | 61.95 | 7000 | 0.6184 | 0.4425 |
|
| 71 |
+
| 0.5506 | 66.37 | 7500 | 0.6963 | 0.4585 |
|
| 72 |
+
| 0.4998 | 70.8 | 8000 | 0.6778 | 0.4468 |
|
| 73 |
+
| 0.4729 | 75.22 | 8500 | 0.6383 | 0.4393 |
|
| 74 |
+
| 0.4535 | 79.65 | 9000 | 0.6593 | 0.4369 |
|
| 75 |
+
| 0.4358 | 84.07 | 9500 | 0.6914 | 0.4422 |
|
| 76 |
+
| 0.402 | 88.5 | 10000 | 0.6744 | 0.4269 |
|
| 77 |
+
| 0.3946 | 92.92 | 10500 | 0.6895 | 0.4275 |
|
| 78 |
+
| 0.3734 | 97.35 | 11000 | 0.6889 | 0.4320 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.16.0.dev0
|
| 84 |
+
- Pytorch 1.10.1+cu102
|
| 85 |
+
- Datasets 1.17.1.dev0
|
| 86 |
+
- Tokenizers 0.11.0
|