update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-large-xlsr-53_train_data_full
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-large-xlsr-53_train_data_full
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4168
|
| 18 |
+
- Wer: 0.3383
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 52 |
+
| 3.0459 | 0.73 | 500 | 3.2037 | 0.9995 |
|
| 53 |
+
| 0.7938 | 1.45 | 1000 | 0.7432 | 0.6373 |
|
| 54 |
+
| 0.503 | 2.18 | 1500 | 0.5517 | 0.5115 |
|
| 55 |
+
| 0.4475 | 2.91 | 2000 | 0.4916 | 0.4624 |
|
| 56 |
+
| 0.3575 | 3.63 | 2500 | 0.4612 | 0.4362 |
|
| 57 |
+
| 0.3206 | 4.36 | 3000 | 0.4546 | 0.4198 |
|
| 58 |
+
| 0.3155 | 5.09 | 3500 | 0.4073 | 0.3929 |
|
| 59 |
+
| 0.2827 | 5.81 | 4000 | 0.4172 | 0.3808 |
|
| 60 |
+
| 0.2575 | 6.54 | 4500 | 0.4183 | 0.3741 |
|
| 61 |
+
| 0.2399 | 7.27 | 5000 | 0.4181 | 0.3680 |
|
| 62 |
+
| 0.2455 | 7.99 | 5500 | 0.3981 | 0.3604 |
|
| 63 |
+
| 0.2512 | 8.72 | 6000 | 0.4203 | 0.3612 |
|
| 64 |
+
| 0.221 | 9.45 | 6500 | 0.4073 | 0.3560 |
|
| 65 |
+
| 0.19 | 10.17 | 7000 | 0.4206 | 0.3547 |
|
| 66 |
+
| 0.207 | 10.9 | 7500 | 0.3992 | 0.3517 |
|
| 67 |
+
| 0.187 | 11.63 | 8000 | 0.4078 | 0.3517 |
|
| 68 |
+
| 0.2029 | 12.35 | 8500 | 0.4143 | 0.3469 |
|
| 69 |
+
| 0.171 | 13.08 | 9000 | 0.4007 | 0.3430 |
|
| 70 |
+
| 0.1658 | 13.81 | 9500 | 0.3862 | 0.3422 |
|
| 71 |
+
| 0.2021 | 14.53 | 10000 | 0.4132 | 0.3454 |
|
| 72 |
+
| 0.165 | 15.26 | 10500 | 0.3997 | 0.3407 |
|
| 73 |
+
| 0.1562 | 15.99 | 11000 | 0.4069 | 0.3416 |
|
| 74 |
+
| 0.1613 | 16.71 | 11500 | 0.4040 | 0.3393 |
|
| 75 |
+
| 0.1713 | 17.44 | 12000 | 0.4094 | 0.3411 |
|
| 76 |
+
| 0.1541 | 18.17 | 12500 | 0.4043 | 0.3367 |
|
| 77 |
+
| 0.144 | 18.89 | 13000 | 0.4086 | 0.3374 |
|
| 78 |
+
| 0.1483 | 19.62 | 13500 | 0.4168 | 0.3383 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.18.0
|
| 84 |
+
- Pytorch 1.11.0+cu102
|
| 85 |
+
- Datasets 2.1.0
|
| 86 |
+
- Tokenizers 0.12.1
|