update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_8_0
|
| 7 |
+
model-index:
|
| 8 |
+
- name: xlsr_ur_training
|
| 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 |
+
# xlsr_ur_training
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_8_0 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.2610
|
| 20 |
+
- Wer: 0.7325
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 100
|
| 46 |
+
- num_epochs: 30
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 14.5044 | 1.69 | 100 | 3.9173 | 1.0 |
|
| 54 |
+
| 3.3645 | 3.39 | 200 | 3.2475 | 1.0 |
|
| 55 |
+
| 3.2318 | 5.08 | 300 | 3.2143 | 1.0 |
|
| 56 |
+
| 3.1887 | 6.78 | 400 | 3.1672 | 1.0 |
|
| 57 |
+
| 3.1233 | 8.47 | 500 | 3.0927 | 1.0 |
|
| 58 |
+
| 3.0938 | 10.17 | 600 | 3.0836 | 0.9970 |
|
| 59 |
+
| 3.0706 | 11.86 | 700 | 3.0319 | 0.9996 |
|
| 60 |
+
| 2.9622 | 13.56 | 800 | 2.7973 | 0.9985 |
|
| 61 |
+
| 2.6267 | 15.25 | 900 | 2.2553 | 0.9974 |
|
| 62 |
+
| 1.9748 | 16.95 | 1000 | 1.6858 | 0.9170 |
|
| 63 |
+
| 1.4739 | 18.64 | 1100 | 1.4620 | 0.8125 |
|
| 64 |
+
| 1.2102 | 20.34 | 1200 | 1.3890 | 0.7779 |
|
| 65 |
+
| 1.036 | 22.03 | 1300 | 1.3347 | 0.7672 |
|
| 66 |
+
| 0.9462 | 23.73 | 1400 | 1.2970 | 0.7476 |
|
| 67 |
+
| 0.8725 | 25.42 | 1500 | 1.2792 | 0.7461 |
|
| 68 |
+
| 0.8374 | 27.12 | 1600 | 1.2574 | 0.7384 |
|
| 69 |
+
| 0.7976 | 28.81 | 1700 | 1.2610 | 0.7325 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.21.0
|
| 75 |
+
- Pytorch 1.11.0+cu113
|
| 76 |
+
- Datasets 2.4.0
|
| 77 |
+
- Tokenizers 0.12.1
|