Commit
•
c71bac1
1
Parent(s):
a89b51e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ''
|
| 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 |
+
#
|
| 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 common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3633
|
| 20 |
+
- Wer: 0.4174
|
| 21 |
+
- Cer: 0.0943
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 7.5e-05
|
| 41 |
+
- train_batch_size: 64
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- training_steps: 6124
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 3.5184 | 12.9 | 400 | 3.4210 | 1.0 | 1.0 |
|
| 57 |
+
| 2.3797 | 25.81 | 800 | 1.1068 | 0.8389 | 0.2584 |
|
| 58 |
+
| 1.5022 | 38.71 | 1200 | 0.5278 | 0.6280 | 0.1517 |
|
| 59 |
+
| 1.3181 | 51.61 | 1600 | 0.4254 | 0.5587 | 0.1297 |
|
| 60 |
+
| 1.2037 | 64.52 | 2000 | 0.3836 | 0.5143 | 0.1176 |
|
| 61 |
+
| 1.1245 | 77.42 | 2400 | 0.3643 | 0.4871 | 0.1111 |
|
| 62 |
+
| 1.0582 | 90.32 | 2800 | 0.3562 | 0.4676 | 0.1062 |
|
| 63 |
+
| 1.0027 | 103.23 | 3200 | 0.3530 | 0.4625 | 0.1058 |
|
| 64 |
+
| 0.9382 | 116.13 | 3600 | 0.3388 | 0.4442 | 0.1002 |
|
| 65 |
+
| 0.8915 | 129.03 | 4000 | 0.3430 | 0.4427 | 0.1000 |
|
| 66 |
+
| 0.853 | 141.94 | 4400 | 0.3536 | 0.4375 | 0.1000 |
|
| 67 |
+
| 0.8127 | 154.84 | 4800 | 0.3511 | 0.4344 | 0.0986 |
|
| 68 |
+
| 0.7861 | 167.74 | 5200 | 0.3595 | 0.4372 | 0.0993 |
|
| 69 |
+
| 0.7619 | 180.65 | 5600 | 0.3628 | 0.4316 | 0.0985 |
|
| 70 |
+
| 0.7537 | 193.55 | 6000 | 0.3633 | 0.4174 | 0.0943 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.19.0.dev0
|
| 76 |
+
- Pytorch 1.11.0+cu102
|
| 77 |
+
- Datasets 2.1.1.dev0
|
| 78 |
+
- Tokenizers 0.12.1
|