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_F03
|
| 12 |
results: []
|
|
@@ -17,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# torgo_xlsr_finetune_F03
|
| 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_F03
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# torgo_xlsr_finetune_F03
|
| 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: 0.2366
|
| 20 |
+
- Wer: 0.0535
|
| 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 |
+
| 3.4672 | 0.85 | 1000 | 3.4147 | 1.0 |
|
| 55 |
+
| 2.149 | 1.69 | 2000 | 0.9590 | 0.7064 |
|
| 56 |
+
| 0.9304 | 2.54 | 3000 | 0.3999 | 0.3896 |
|
| 57 |
+
| 0.6396 | 3.39 | 4000 | 0.2892 | 0.2332 |
|
| 58 |
+
| 0.5114 | 4.24 | 5000 | 0.2362 | 0.1701 |
|
| 59 |
+
| 0.454 | 5.08 | 6000 | 0.2241 | 0.1468 |
|
| 60 |
+
| 0.3899 | 5.93 | 7000 | 0.2356 | 0.0919 |
|
| 61 |
+
| 0.3466 | 6.78 | 8000 | 0.2607 | 0.0796 |
|
| 62 |
+
| 0.316 | 7.63 | 9000 | 0.2358 | 0.0919 |
|
| 63 |
+
| 0.2889 | 8.47 | 10000 | 0.2159 | 0.0617 |
|
| 64 |
+
| 0.2476 | 9.32 | 11000 | 0.2129 | 0.0713 |
|
| 65 |
+
| 0.2608 | 10.17 | 12000 | 0.1812 | 0.0878 |
|
| 66 |
+
| 0.2338 | 11.02 | 13000 | 0.2010 | 0.0631 |
|
| 67 |
+
| 0.2302 | 11.86 | 14000 | 0.1623 | 0.0576 |
|
| 68 |
+
| 0.2037 | 12.71 | 15000 | 0.2469 | 0.0604 |
|
| 69 |
+
| 0.1995 | 13.56 | 16000 | 0.1836 | 0.0562 |
|
| 70 |
+
| 0.1668 | 14.41 | 17000 | 0.2070 | 0.0741 |
|
| 71 |
+
| 0.1597 | 15.25 | 18000 | 0.2269 | 0.0658 |
|
| 72 |
+
| 0.1574 | 16.1 | 19000 | 0.2087 | 0.0713 |
|
| 73 |
+
| 0.1397 | 16.95 | 20000 | 0.1998 | 0.0576 |
|
| 74 |
+
| 0.1325 | 17.8 | 21000 | 0.1844 | 0.0549 |
|
| 75 |
+
| 0.1273 | 18.64 | 22000 | 0.2306 | 0.0535 |
|
| 76 |
+
| 0.1204 | 19.49 | 23000 | 0.2366 | 0.0535 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- Transformers 4.26.1
|