Commit
•
84aeff3
1
Parent(s):
0a05af1
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- timit
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large_phoneme-timit_english_timit-4k_001
|
| 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_phoneme-timit_english_timit-4k_001
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on the timit dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5320
|
| 20 |
+
- Per: 0.1411
|
| 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: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 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: 5000
|
| 46 |
+
- training_steps: 10000
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Per |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 4.5458 | 3.46 | 1000 | 0.9087 | 0.2354 |
|
| 54 |
+
| 0.7877 | 6.92 | 2000 | 0.4441 | 0.1506 |
|
| 55 |
+
| 0.5125 | 10.38 | 3000 | 0.4241 | 0.1451 |
|
| 56 |
+
| 0.4485 | 13.84 | 4000 | 0.4244 | 0.1461 |
|
| 57 |
+
| 0.4193 | 17.3 | 5000 | 0.4618 | 0.1510 |
|
| 58 |
+
| 0.3899 | 20.76 | 6000 | 0.4700 | 0.1469 |
|
| 59 |
+
| 0.3244 | 24.22 | 7000 | 0.4496 | 0.1438 |
|
| 60 |
+
| 0.2717 | 27.68 | 8000 | 0.4988 | 0.1455 |
|
| 61 |
+
| 0.2222 | 31.14 | 9000 | 0.5182 | 0.1414 |
|
| 62 |
+
| 0.1872 | 34.6 | 10000 | 0.5320 | 0.1411 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.28.1
|
| 68 |
+
- Pytorch 2.0.1
|
| 69 |
+
- Datasets 2.18.0
|
| 70 |
+
- Tokenizers 0.13.3
|