Commit
•
fc0165b
1
Parent(s):
56d3c2a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-tira-colab
|
| 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-large-xls-r-300m-tira-colab
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2681
|
| 20 |
+
- Wer: 0.2787
|
| 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: 0.0003
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 30
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 4.2937 | 1.45 | 400 | 1.0460 | 0.9297 |
|
| 55 |
+
| 0.9157 | 2.9 | 800 | 0.5732 | 0.6728 |
|
| 56 |
+
| 0.6258 | 4.35 | 1200 | 0.4319 | 0.5434 |
|
| 57 |
+
| 0.5114 | 5.8 | 1600 | 0.3822 | 0.5465 |
|
| 58 |
+
| 0.4059 | 7.25 | 2000 | 0.3439 | 0.4700 |
|
| 59 |
+
| 0.3407 | 8.7 | 2400 | 0.2997 | 0.4778 |
|
| 60 |
+
| 0.2938 | 10.14 | 2800 | 0.2956 | 0.4121 |
|
| 61 |
+
| 0.2465 | 11.59 | 3200 | 0.2834 | 0.3537 |
|
| 62 |
+
| 0.2148 | 13.04 | 3600 | 0.2662 | 0.3779 |
|
| 63 |
+
| 0.1711 | 14.49 | 4000 | 0.2724 | 0.3160 |
|
| 64 |
+
| 0.1621 | 15.94 | 4400 | 0.2452 | 0.3571 |
|
| 65 |
+
| 0.1301 | 17.39 | 4800 | 0.2638 | 0.2927 |
|
| 66 |
+
| 0.1119 | 18.84 | 5200 | 0.2724 | 0.2765 |
|
| 67 |
+
| 0.1026 | 20.29 | 5600 | 0.2703 | 0.2986 |
|
| 68 |
+
| 0.0906 | 21.74 | 6000 | 0.2642 | 0.2638 |
|
| 69 |
+
| 0.0785 | 23.19 | 6400 | 0.2653 | 0.2709 |
|
| 70 |
+
| 0.0648 | 24.64 | 6800 | 0.2644 | 0.2669 |
|
| 71 |
+
| 0.0578 | 26.09 | 7200 | 0.2712 | 0.3123 |
|
| 72 |
+
| 0.0514 | 27.54 | 7600 | 0.2703 | 0.2672 |
|
| 73 |
+
| 0.0459 | 28.99 | 8000 | 0.2681 | 0.2787 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.30.2
|
| 79 |
+
- Pytorch 2.0.1+cu118
|
| 80 |
+
- Datasets 2.13.1
|
| 81 |
+
- Tokenizers 0.13.3
|