Commit
•
7cf5aec
1
Parent(s):
4616e16
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 0.4185
|
| 20 |
+
- Wer: 0.3231
|
| 21 |
+
- Cer: 0.1072
|
| 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: 5108
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 3.2894 | 7.83 | 400 | 3.1501 | 1.0 | 1.0 |
|
| 57 |
+
| 1.8586 | 15.68 | 800 | 0.8871 | 0.6721 | 0.2402 |
|
| 58 |
+
| 1.3431 | 23.52 | 1200 | 0.5813 | 0.5502 | 0.1939 |
|
| 59 |
+
| 1.2052 | 31.37 | 1600 | 0.4956 | 0.4788 | 0.1665 |
|
| 60 |
+
| 1.1097 | 39.21 | 2000 | 0.4447 | 0.4143 | 0.1397 |
|
| 61 |
+
| 1.0528 | 47.06 | 2400 | 0.4439 | 0.3961 | 0.1333 |
|
| 62 |
+
| 0.9939 | 54.89 | 2800 | 0.4348 | 0.4014 | 0.1379 |
|
| 63 |
+
| 0.9441 | 62.74 | 3200 | 0.4236 | 0.3653 | 0.1223 |
|
| 64 |
+
| 0.913 | 70.58 | 3600 | 0.4309 | 0.3475 | 0.1157 |
|
| 65 |
+
| 0.8678 | 78.43 | 4000 | 0.4270 | 0.3337 | 0.1110 |
|
| 66 |
+
| 0.8414 | 86.27 | 4400 | 0.4158 | 0.3220 | 0.1070 |
|
| 67 |
+
| 0.817 | 94.12 | 4800 | 0.4185 | 0.3231 | 0.1072 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.19.0.dev0
|
| 73 |
+
- Pytorch 1.11.0+cu102
|
| 74 |
+
- Datasets 2.1.1.dev0
|
| 75 |
+
- Tokenizers 0.12.1
|