update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-large-xls-r-300m-bemba-fds
|
| 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-xls-r-300m-bemba-fds
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.3594
|
| 18 |
+
- Wer: 0.4067
|
| 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: 0.0003
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 16
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- num_epochs: 30
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 2.9961 | 0.67 | 500 | 0.5157 | 0.7133 |
|
| 54 |
+
| 0.5903 | 1.34 | 1000 | 0.3663 | 0.4989 |
|
| 55 |
+
| 0.4804 | 2.02 | 1500 | 0.3547 | 0.4653 |
|
| 56 |
+
| 0.4146 | 2.69 | 2000 | 0.3274 | 0.4345 |
|
| 57 |
+
| 0.3792 | 3.36 | 2500 | 0.3586 | 0.4640 |
|
| 58 |
+
| 0.3509 | 4.03 | 3000 | 0.3360 | 0.4316 |
|
| 59 |
+
| 0.3114 | 4.7 | 3500 | 0.3382 | 0.4303 |
|
| 60 |
+
| 0.2935 | 5.38 | 4000 | 0.3263 | 0.4091 |
|
| 61 |
+
| 0.2723 | 6.05 | 4500 | 0.3348 | 0.4175 |
|
| 62 |
+
| 0.2502 | 6.72 | 5000 | 0.3317 | 0.4147 |
|
| 63 |
+
| 0.2334 | 7.39 | 5500 | 0.3542 | 0.4030 |
|
| 64 |
+
| 0.2287 | 8.06 | 6000 | 0.3594 | 0.4067 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.11.3
|
| 70 |
+
- Pytorch 1.10.0+cu111
|
| 71 |
+
- Datasets 1.13.3
|
| 72 |
+
- Tokenizers 0.10.3
|