update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,9 +4,24 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- common_voice
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: wav2vec2-large-xls-r-may23-luganda-colab
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,6 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# wav2vec2-large-xls-r-may23-luganda-colab
|
| 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 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -45,6 +63,24 @@ The following hyperparameters were used during training:
|
|
| 45 |
- num_epochs: 100
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.29.2
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- common_voice
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: wav2vec2-large-xls-r-may23-luganda-colab
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice
|
| 17 |
+
type: common_voice
|
| 18 |
+
config: lg
|
| 19 |
+
split: test
|
| 20 |
+
args: lg
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 0.502121009153829
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
# wav2vec2-large-xls-r-may23-luganda-colab
|
| 31 |
|
| 32 |
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.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.7210
|
| 35 |
+
- Wer: 0.5021
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 63 |
- num_epochs: 100
|
| 64 |
- mixed_precision_training: Native AMP
|
| 65 |
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 70 |
+
| 0.0539 | 7.77 | 400 | 0.6641 | 0.5738 |
|
| 71 |
+
| 0.0725 | 15.53 | 800 | 0.6735 | 0.5932 |
|
| 72 |
+
| 0.058 | 23.3 | 1200 | 0.6754 | 0.5751 |
|
| 73 |
+
| 0.0517 | 31.07 | 1600 | 0.6591 | 0.5901 |
|
| 74 |
+
| 0.0437 | 38.83 | 2000 | 0.7140 | 0.5658 |
|
| 75 |
+
| 0.0366 | 46.6 | 2400 | 0.7154 | 0.5602 |
|
| 76 |
+
| 0.0295 | 54.37 | 2800 | 0.6942 | 0.5140 |
|
| 77 |
+
| 0.0251 | 62.14 | 3200 | 0.7095 | 0.5204 |
|
| 78 |
+
| 0.0191 | 69.9 | 3600 | 0.7459 | 0.5267 |
|
| 79 |
+
| 0.0157 | 77.67 | 4000 | 0.6825 | 0.5155 |
|
| 80 |
+
| 0.0126 | 85.44 | 4400 | 0.7197 | 0.5135 |
|
| 81 |
+
| 0.0098 | 93.2 | 4800 | 0.7210 | 0.5021 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
### Framework versions
|
| 85 |
|
| 86 |
- Transformers 4.29.2
|