update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
-
- audio
|
| 7 |
-
- speech
|
| 8 |
-
- wav2vec2
|
| 9 |
- generated_from_trainer
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: torgo_xlsr_finetune_M03
|
| 12 |
results: []
|
|
@@ -17,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# torgo_xlsr_finetune_M03
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -47,6 +47,35 @@ The following hyperparameters were used during training:
|
|
| 47 |
- lr_scheduler_warmup_steps: 1000
|
| 48 |
- num_epochs: 20
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
### Framework versions
|
| 51 |
|
| 52 |
- Transformers 4.26.1
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
|
|
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
model-index:
|
| 8 |
- name: torgo_xlsr_finetune_M03
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# torgo_xlsr_finetune_M03
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.1905
|
| 20 |
+
- Wer: 0.2097
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 47 |
- lr_scheduler_warmup_steps: 1000
|
| 48 |
- num_epochs: 20
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 54 |
+
| 3.5007 | 0.85 | 1000 | 3.2973 | 1.0 |
|
| 55 |
+
| 2.2459 | 1.71 | 2000 | 1.9925 | 0.8829 |
|
| 56 |
+
| 0.9013 | 2.56 | 3000 | 1.1537 | 0.6138 |
|
| 57 |
+
| 0.6388 | 3.41 | 4000 | 1.2210 | 0.5017 |
|
| 58 |
+
| 0.5391 | 4.27 | 5000 | 1.2570 | 0.4032 |
|
| 59 |
+
| 0.4528 | 5.12 | 6000 | 1.1298 | 0.3718 |
|
| 60 |
+
| 0.3892 | 5.97 | 7000 | 1.1642 | 0.3090 |
|
| 61 |
+
| 0.3382 | 6.83 | 8000 | 1.0970 | 0.3149 |
|
| 62 |
+
| 0.3279 | 7.68 | 9000 | 1.1686 | 0.3107 |
|
| 63 |
+
| 0.2816 | 8.53 | 10000 | 1.3912 | 0.3107 |
|
| 64 |
+
| 0.2667 | 9.39 | 11000 | 1.2643 | 0.2776 |
|
| 65 |
+
| 0.2517 | 10.24 | 12000 | 1.2157 | 0.2504 |
|
| 66 |
+
| 0.2312 | 11.09 | 13000 | 1.2624 | 0.2640 |
|
| 67 |
+
| 0.2239 | 11.95 | 14000 | 1.2676 | 0.2640 |
|
| 68 |
+
| 0.1849 | 12.8 | 15000 | 1.1427 | 0.2623 |
|
| 69 |
+
| 0.1841 | 13.65 | 16000 | 1.2277 | 0.2547 |
|
| 70 |
+
| 0.1793 | 14.51 | 17000 | 1.3833 | 0.2572 |
|
| 71 |
+
| 0.1704 | 15.36 | 18000 | 1.3813 | 0.2691 |
|
| 72 |
+
| 0.1688 | 16.21 | 19000 | 1.3418 | 0.2589 |
|
| 73 |
+
| 0.1527 | 17.06 | 20000 | 1.2787 | 0.2343 |
|
| 74 |
+
| 0.1304 | 17.92 | 21000 | 1.2078 | 0.2190 |
|
| 75 |
+
| 0.1332 | 18.77 | 22000 | 1.2041 | 0.2105 |
|
| 76 |
+
| 0.1253 | 19.62 | 23000 | 1.1905 | 0.2097 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- Transformers 4.26.1
|