End of training
Browse files
README.md
CHANGED
|
@@ -3,9 +3,26 @@ license: apache-2.0
|
|
| 3 |
base_model: facebook/wav2vec2-xls-r-1b
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: XLS-R-LUGANDA-ASR-CV-14-1B
|
| 8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,7 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# XLS-R-LUGANDA-ASR-CV-14-1B
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -44,6 +65,37 @@ The following hyperparameters were used during training:
|
|
| 44 |
- training_steps: 10000
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- Transformers 4.38.1
|
|
|
|
| 3 |
base_model: facebook/wav2vec2-xls-r-1b
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- common_voice_14_0
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
model-index:
|
| 11 |
- name: XLS-R-LUGANDA-ASR-CV-14-1B
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: common_voice_14_0
|
| 18 |
+
type: common_voice_14_0
|
| 19 |
+
config: lg
|
| 20 |
+
split: test
|
| 21 |
+
args: lg
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.30603965548369283
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# XLS-R-LUGANDA-ASR-CV-14-1B
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_14_0 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: inf
|
| 36 |
+
- Wer: 0.3060
|
| 37 |
+
- Cer: 0.0713
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 65 |
- training_steps: 10000
|
| 66 |
- mixed_precision_training: Native AMP
|
| 67 |
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
|
| 72 |
+
| 1.5535 | 0.18 | 400 | 0.1685 | inf | 0.6590 |
|
| 73 |
+
| 0.539 | 0.36 | 800 | 0.1516 | inf | 0.5934 |
|
| 74 |
+
| 0.49 | 0.54 | 1200 | 0.1365 | inf | 0.5466 |
|
| 75 |
+
| 0.4569 | 0.72 | 1600 | 0.1364 | inf | 0.5523 |
|
| 76 |
+
| 0.4845 | 0.45 | 2000 | 0.1525 | inf | 0.5907 |
|
| 77 |
+
| 0.4592 | 0.54 | 2400 | 0.1485 | inf | 0.5766 |
|
| 78 |
+
| 0.4447 | 0.63 | 2800 | 0.1397 | inf | 0.5482 |
|
| 79 |
+
| 0.426 | 0.72 | 3200 | 0.1352 | inf | 0.5290 |
|
| 80 |
+
| 0.4454 | 0.81 | 3600 | inf | 0.5330 | 0.1333 |
|
| 81 |
+
| 0.4188 | 0.9 | 4000 | inf | 0.4903 | 0.1240 |
|
| 82 |
+
| 0.4083 | 0.99 | 4400 | inf | 0.4857 | 0.1226 |
|
| 83 |
+
| 0.367 | 1.08 | 4800 | inf | 0.4499 | 0.1114 |
|
| 84 |
+
| 0.3468 | 1.17 | 5200 | inf | 0.4345 | 0.1063 |
|
| 85 |
+
| 0.3401 | 1.27 | 5600 | inf | 0.4130 | 0.1009 |
|
| 86 |
+
| 0.3269 | 1.36 | 6000 | inf | 0.4113 | 0.1004 |
|
| 87 |
+
| 0.3171 | 1.45 | 6400 | inf | 0.3934 | 0.0956 |
|
| 88 |
+
| 0.2996 | 1.54 | 6800 | inf | 0.3803 | 0.0913 |
|
| 89 |
+
| 0.288 | 1.63 | 7200 | inf | 0.3681 | 0.0891 |
|
| 90 |
+
| 0.2812 | 1.72 | 7600 | inf | 0.3573 | 0.0853 |
|
| 91 |
+
| 0.2699 | 1.81 | 8000 | inf | 0.3504 | 0.0835 |
|
| 92 |
+
| 0.2584 | 1.9 | 8400 | inf | 0.3343 | 0.0786 |
|
| 93 |
+
| 0.2424 | 1.99 | 8800 | inf | 0.3232 | 0.0759 |
|
| 94 |
+
| 0.2201 | 2.08 | 9200 | inf | 0.3176 | 0.0740 |
|
| 95 |
+
| 0.2031 | 2.17 | 9600 | inf | 0.3085 | 0.0719 |
|
| 96 |
+
| 0.2007 | 2.26 | 10000 | inf | 0.3060 | 0.0713 |
|
| 97 |
+
|
| 98 |
+
|
| 99 |
### Framework versions
|
| 100 |
|
| 101 |
- Transformers 4.38.1
|