update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
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_8_0 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Wer: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -58,27 +58,25 @@ The following hyperparameters were used during training:
|
|
58 |
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
- lr_scheduler_warmup_ratio: 0.1
|
61 |
-
- num_epochs:
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
| 3.
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
-
| 1.0963 | 81.25 | 650 | 1.2016 | 0.8416 |
|
81 |
-
| 1.2322 | 87.5 | 700 | 1.2060 | 0.8409 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 0.5262462505356378
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
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_8_0 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.9269
|
35 |
+
- Wer: 0.5262
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
58 |
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 80
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
+
| 9.2929 | 6.25 | 50 | 3.0514 | 1.0 |
|
69 |
+
| 3.315 | 12.5 | 100 | 3.2255 | 1.0 |
|
70 |
+
| 3.1506 | 18.75 | 150 | 2.9924 | 1.0 |
|
71 |
+
| 2.9773 | 25.0 | 200 | 2.2199 | 1.0 |
|
72 |
+
| 2.1616 | 31.25 | 250 | 1.1423 | 0.8603 |
|
73 |
+
| 1.6887 | 37.5 | 300 | 0.9730 | 0.7020 |
|
74 |
+
| 1.1178 | 43.75 | 350 | 0.8971 | 0.6323 |
|
75 |
+
| 0.9512 | 50.0 | 400 | 0.9040 | 0.5960 |
|
76 |
+
| 0.7696 | 56.25 | 450 | 0.9232 | 0.5713 |
|
77 |
+
| 0.7348 | 62.5 | 500 | 0.9203 | 0.5412 |
|
78 |
+
| 0.9312 | 68.75 | 550 | 0.9673 | 0.5376 |
|
79 |
+
| 0.6519 | 75.0 | 600 | 0.9269 | 0.5262 |
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|