Commit
•
b12fdd1
1
Parent(s):
5889a8c
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ja
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- mozilla-foundation/common_voice_8_0
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-large-xlsr-53-ja
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wav2vec2-large-xlsr-53-ja
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - JA dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4214
|
| 22 |
+
- Wer: 0.3375
|
| 23 |
+
- Cer: 0.1587
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0003
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 2000
|
| 51 |
+
- num_epochs: 50.0
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 58 |
+
| 4.7776 | 4.73 | 1500 | 2.9540 | 0.9772 | 0.8489 |
|
| 59 |
+
| 1.9076 | 9.46 | 3000 | 0.7146 | 0.5371 | 0.2484 |
|
| 60 |
+
| 1.507 | 14.2 | 4500 | 0.5843 | 0.4689 | 0.2196 |
|
| 61 |
+
| 1.3742 | 18.93 | 6000 | 0.5286 | 0.4321 | 0.1988 |
|
| 62 |
+
| 1.2776 | 23.66 | 7500 | 0.5007 | 0.4056 | 0.1870 |
|
| 63 |
+
| 1.2003 | 28.39 | 9000 | 0.4676 | 0.3848 | 0.1802 |
|
| 64 |
+
| 1.1281 | 33.12 | 10500 | 0.4524 | 0.3694 | 0.1720 |
|
| 65 |
+
| 1.0657 | 37.85 | 12000 | 0.4449 | 0.3590 | 0.1681 |
|
| 66 |
+
| 1.0129 | 42.59 | 13500 | 0.4266 | 0.3423 | 0.1617 |
|
| 67 |
+
| 0.9691 | 47.32 | 15000 | 0.4214 | 0.3375 | 0.1587 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.16.0.dev0
|
| 73 |
+
- Pytorch 1.10.1+cu102
|
| 74 |
+
- Datasets 1.18.3
|
| 75 |
+
- Tokenizers 0.11.0
|