Badr Abdullah
commited on
Commit
•
f5c1648
1
Parent(s):
1f45a71
Model save
Browse files
README.md
CHANGED
@@ -28,7 +28,7 @@ model-index:
|
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/badr-nlp/xlsr-continual-finetuning-new/runs/
|
32 |
# mHuBERT-147-upper-sorbian
|
33 |
|
34 |
This model is a fine-tuned version of [utter-project/mHuBERT-147](https://huggingface.co/utter-project/mHuBERT-147) on the common_voice_17_0 dataset.
|
@@ -64,34 +64,33 @@ The following hyperparameters were used during training:
|
|
64 |
- lr_scheduler_type: linear
|
65 |
- lr_scheduler_warmup_steps: 500
|
66 |
- num_epochs: 100
|
67 |
-
- mixed_precision_training: Native AMP
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
72 |
|:-------------:|:-------:|:----:|:---------------:|:---:|:---:|
|
73 |
-
|
|
74 |
-
| 3.
|
75 |
-
| 3.
|
76 |
-
| 3.2292 | 15.6863 | 400 | 3.
|
77 |
-
| 3.2105 | 19.6078 | 500 | 3.
|
78 |
-
| 3.
|
79 |
| 3.2626 | 27.4510 | 700 | 3.2177 | 1.0 | 1.0 |
|
80 |
-
| 3.21 | 31.3725 | 800 | 3.
|
81 |
| 3.1871 | 35.2941 | 900 | 3.2211 | 1.0 | 1.0 |
|
82 |
-
| 3.
|
83 |
-
| 3.2408 | 43.1373 | 1100 | 3.
|
84 |
| 3.2 | 47.0588 | 1200 | 3.2193 | 1.0 | 1.0 |
|
85 |
| 3.202 | 50.9804 | 1300 | 3.2181 | 1.0 | 1.0 |
|
86 |
| 3.2286 | 54.9020 | 1400 | 3.2190 | 1.0 | 1.0 |
|
87 |
| 3.1863 | 58.8235 | 1500 | 3.2187 | 1.0 | 1.0 |
|
88 |
-
| 3.1868 | 62.7451 | 1600 | 3.
|
89 |
| 3.226 | 66.6667 | 1700 | 3.2199 | 1.0 | 1.0 |
|
90 |
-
| 3.1944 | 70.5882 | 1800 | 3.
|
91 |
| 3.1997 | 74.5098 | 1900 | 3.2180 | 1.0 | 1.0 |
|
92 |
| 3.2184 | 78.4314 | 2000 | 3.2200 | 1.0 | 1.0 |
|
93 |
-
| 3.2252 | 82.3529 | 2100 | 3.
|
94 |
-
| 3.208 | 86.2745 | 2200 | 3.
|
95 |
| 3.2122 | 90.1961 | 2300 | 3.2170 | 1.0 | 1.0 |
|
96 |
| 3.2307 | 94.1176 | 2400 | 3.2169 | 1.0 | 1.0 |
|
97 |
| 3.1852 | 98.0392 | 2500 | 3.2172 | 1.0 | 1.0 |
|
|
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/badr-nlp/xlsr-continual-finetuning-new/runs/mfm1kgzn)
|
32 |
# mHuBERT-147-upper-sorbian
|
33 |
|
34 |
This model is a fine-tuned version of [utter-project/mHuBERT-147](https://huggingface.co/utter-project/mHuBERT-147) on the common_voice_17_0 dataset.
|
|
|
64 |
- lr_scheduler_type: linear
|
65 |
- lr_scheduler_warmup_steps: 500
|
66 |
- num_epochs: 100
|
|
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
71 |
|:-------------:|:-------:|:----:|:---------------:|:---:|:---:|
|
72 |
+
| 3.8611 | 3.9216 | 100 | 3.8610 | 1.0 | 1.0 |
|
73 |
+
| 3.2233 | 7.8431 | 200 | 3.2270 | 1.0 | 1.0 |
|
74 |
+
| 3.1742 | 11.7647 | 300 | 3.2232 | 1.0 | 1.0 |
|
75 |
+
| 3.2292 | 15.6863 | 400 | 3.2238 | 1.0 | 1.0 |
|
76 |
+
| 3.2105 | 19.6078 | 500 | 3.2270 | 1.0 | 1.0 |
|
77 |
+
| 3.191 | 23.5294 | 600 | 3.2201 | 1.0 | 1.0 |
|
78 |
| 3.2626 | 27.4510 | 700 | 3.2177 | 1.0 | 1.0 |
|
79 |
+
| 3.21 | 31.3725 | 800 | 3.2230 | 1.0 | 1.0 |
|
80 |
| 3.1871 | 35.2941 | 900 | 3.2211 | 1.0 | 1.0 |
|
81 |
+
| 3.2221 | 39.2157 | 1000 | 3.2245 | 1.0 | 1.0 |
|
82 |
+
| 3.2408 | 43.1373 | 1100 | 3.2217 | 1.0 | 1.0 |
|
83 |
| 3.2 | 47.0588 | 1200 | 3.2193 | 1.0 | 1.0 |
|
84 |
| 3.202 | 50.9804 | 1300 | 3.2181 | 1.0 | 1.0 |
|
85 |
| 3.2286 | 54.9020 | 1400 | 3.2190 | 1.0 | 1.0 |
|
86 |
| 3.1863 | 58.8235 | 1500 | 3.2187 | 1.0 | 1.0 |
|
87 |
+
| 3.1868 | 62.7451 | 1600 | 3.2175 | 1.0 | 1.0 |
|
88 |
| 3.226 | 66.6667 | 1700 | 3.2199 | 1.0 | 1.0 |
|
89 |
+
| 3.1944 | 70.5882 | 1800 | 3.2196 | 1.0 | 1.0 |
|
90 |
| 3.1997 | 74.5098 | 1900 | 3.2180 | 1.0 | 1.0 |
|
91 |
| 3.2184 | 78.4314 | 2000 | 3.2200 | 1.0 | 1.0 |
|
92 |
+
| 3.2252 | 82.3529 | 2100 | 3.2188 | 1.0 | 1.0 |
|
93 |
+
| 3.208 | 86.2745 | 2200 | 3.2175 | 1.0 | 1.0 |
|
94 |
| 3.2122 | 90.1961 | 2300 | 3.2170 | 1.0 | 1.0 |
|
95 |
| 3.2307 | 94.1176 | 2400 | 3.2169 | 1.0 | 1.0 |
|
96 |
| 3.1852 | 98.0392 | 2500 | 3.2172 | 1.0 | 1.0 |
|