Commit
•
9b09bbe
1
Parent(s):
438a1cb
Model save
Browse files
README.md
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
tags:
|
| 5 |
-
- automatic-speech-recognition
|
| 6 |
-
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- wer
|
|
@@ -17,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# wav2vec2-xlsr-53-ft-btb-ccv-cy
|
| 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 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: nan
|
| 23 |
- Wer: 1.0
|
|
@@ -45,7 +43,7 @@ The following hyperparameters were used during training:
|
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- lr_scheduler_warmup_steps:
|
| 49 |
- training_steps: 15000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
|
@@ -53,30 +51,30 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
| 56 |
-
|
|
| 57 |
-
| 1.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
| 0.0 | 0.8016 | 12500 | nan | 1.0 |
|
| 81 |
| 0.0 | 0.8337 | 13000 | nan | 1.0 |
|
| 82 |
| 0.0 | 0.8657 | 13500 | nan | 1.0 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- wer
|
|
|
|
| 15 |
|
| 16 |
# wav2vec2-xlsr-53-ft-btb-ccv-cy
|
| 17 |
|
| 18 |
+
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.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: nan
|
| 21 |
- Wer: 1.0
|
|
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1500
|
| 47 |
- training_steps: 15000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
| 54 |
+
| 5.7778 | 0.0321 | 500 | 2.8852 | 1.0 |
|
| 55 |
+
| 1.4914 | 0.0641 | 1000 | 1.2012 | 0.7806 |
|
| 56 |
+
| 0.8803 | 0.0962 | 1500 | 1.1212 | 0.7590 |
|
| 57 |
+
| 0.7723 | 0.1283 | 2000 | 0.9681 | 0.6770 |
|
| 58 |
+
| 0.6988 | 0.1603 | 2500 | 0.9453 | 0.6599 |
|
| 59 |
+
| 0.6392 | 0.1924 | 3000 | 0.8691 | 0.6200 |
|
| 60 |
+
| 0.6114 | 0.2244 | 3500 | 0.8661 | 0.6192 |
|
| 61 |
+
| 0.5807 | 0.2565 | 4000 | 0.7885 | 0.5794 |
|
| 62 |
+
| 0.5534 | 0.2886 | 4500 | 0.7739 | 0.5490 |
|
| 63 |
+
| 0.5358 | 0.3206 | 5000 | 0.7416 | 0.5415 |
|
| 64 |
+
| 0.5189 | 0.3527 | 5500 | 0.7362 | 0.5303 |
|
| 65 |
+
| 0.4991 | 0.3848 | 6000 | 0.7188 | 0.5066 |
|
| 66 |
+
| 0.48 | 0.4168 | 6500 | 0.6985 | 0.5178 |
|
| 67 |
+
| 0.463 | 0.4489 | 7000 | 0.6682 | 0.4933 |
|
| 68 |
+
| 0.4477 | 0.4810 | 7500 | 0.6625 | 0.4867 |
|
| 69 |
+
| 0.4431 | 0.5130 | 8000 | 0.6374 | 0.4736 |
|
| 70 |
+
| 0.4392 | 0.5451 | 8500 | 0.6392 | 0.4772 |
|
| 71 |
+
| 0.4197 | 0.5771 | 9000 | 0.6159 | 0.4547 |
|
| 72 |
+
| 0.4147 | 0.6092 | 9500 | 0.5995 | 0.4522 |
|
| 73 |
+
| 0.3912 | 0.6413 | 10000 | 0.5848 | 0.4286 |
|
| 74 |
+
| 0.3742 | 0.6733 | 10500 | 0.5850 | 0.4259 |
|
| 75 |
+
| 0.402 | 0.7054 | 11000 | 0.6352 | 0.4489 |
|
| 76 |
+
| 0.5746 | 0.7375 | 11500 | 0.7712 | 0.5171 |
|
| 77 |
+
| 0.5783 | 0.7695 | 12000 | nan | 1.0 |
|
| 78 |
| 0.0 | 0.8016 | 12500 | nan | 1.0 |
|
| 79 |
| 0.0 | 0.8337 | 13000 | nan | 1.0 |
|
| 80 |
| 0.0 | 0.8657 | 13500 | nan | 1.0 |
|