Instructions to use zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f9 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f9")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f9") model = AutoModelForCTC.from_pretrained("zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f9", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +43 -43
- model.safetensors +1 -1
- runs/May04_03-51-37_Lydia/events.out.tfevents.1777884737.Lydia.20124.9 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-lv-60-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Per: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -52,47 +52,47 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Per |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
|
| 55 |
-
| 17.
|
| 56 |
-
| 4.
|
| 57 |
-
| 4.
|
| 58 |
-
| 3.
|
| 59 |
-
| 2.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
|
|
| 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.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
|
| 97 |
|
| 98 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-lv-60-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2496
|
| 20 |
+
- Per: 0.2682
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Per |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 17.5922 | 0.7194 | 400 | 4.5625 | 0.9854 |
|
| 56 |
+
| 4.3936 | 1.4388 | 800 | 4.0924 | 0.9852 |
|
| 57 |
+
| 4.0753 | 2.1583 | 1200 | 3.6483 | 0.9852 |
|
| 58 |
+
| 3.2625 | 2.8777 | 1600 | 1.5656 | 0.4371 |
|
| 59 |
+
| 2.0665 | 3.5971 | 2000 | 0.8789 | 0.3377 |
|
| 60 |
+
| 1.5989 | 4.3165 | 2400 | 0.6199 | 0.3068 |
|
| 61 |
+
| 1.3583 | 5.0360 | 2800 | 0.4887 | 0.2910 |
|
| 62 |
+
| 1.2105 | 5.7554 | 3200 | 0.4126 | 0.2837 |
|
| 63 |
+
| 1.1235 | 6.4748 | 3600 | 0.3650 | 0.2780 |
|
| 64 |
+
| 1.0378 | 7.1942 | 4000 | 0.3373 | 0.2767 |
|
| 65 |
+
| 0.9659 | 7.9137 | 4400 | 0.3245 | 0.2756 |
|
| 66 |
+
| 0.9498 | 8.6331 | 4800 | 0.3119 | 0.2756 |
|
| 67 |
+
| 0.8914 | 9.3525 | 5200 | 0.3038 | 0.2737 |
|
| 68 |
+
| 0.8634 | 10.0719 | 5600 | 0.2876 | 0.2721 |
|
| 69 |
+
| 0.8531 | 10.7914 | 6000 | 0.2893 | 0.2723 |
|
| 70 |
+
| 0.8348 | 11.5108 | 6400 | 0.2859 | 0.2698 |
|
| 71 |
+
| 0.8223 | 12.2302 | 6800 | 0.2871 | 0.2720 |
|
| 72 |
+
| 0.7767 | 12.9496 | 7200 | 0.2740 | 0.2701 |
|
| 73 |
+
| 0.7684 | 13.6691 | 7600 | 0.2726 | 0.2699 |
|
| 74 |
+
| 0.7732 | 14.3885 | 8000 | 0.2668 | 0.2694 |
|
| 75 |
+
| 0.7387 | 15.1079 | 8400 | 0.2648 | 0.2683 |
|
| 76 |
+
| 0.7446 | 15.8273 | 8800 | 0.2584 | 0.2676 |
|
| 77 |
+
| 0.7335 | 16.5468 | 9200 | 0.2541 | 0.2678 |
|
| 78 |
+
| 0.7256 | 17.2662 | 9600 | 0.2580 | 0.2684 |
|
| 79 |
+
| 0.6957 | 17.9856 | 10000 | 0.2580 | 0.2691 |
|
| 80 |
+
| 0.6875 | 18.7050 | 10400 | 0.2569 | 0.2684 |
|
| 81 |
+
| 0.6806 | 19.4245 | 10800 | 0.2568 | 0.2671 |
|
| 82 |
+
| 0.7099 | 20.1439 | 11200 | 0.2558 | 0.2680 |
|
| 83 |
+
| 0.6773 | 20.8633 | 11600 | 0.2539 | 0.2681 |
|
| 84 |
+
| 0.6788 | 21.5827 | 12000 | 0.2538 | 0.2680 |
|
| 85 |
+
| 0.6889 | 22.3022 | 12400 | 0.2532 | 0.2684 |
|
| 86 |
+
| 0.6763 | 23.0216 | 12800 | 0.2498 | 0.2682 |
|
| 87 |
+
| 0.6531 | 23.7410 | 13200 | 0.2513 | 0.2680 |
|
| 88 |
+
| 0.677 | 24.4604 | 13600 | 0.2504 | 0.2681 |
|
| 89 |
+
| 0.6602 | 25.1799 | 14000 | 0.2493 | 0.2681 |
|
| 90 |
+
| 0.6475 | 25.8993 | 14400 | 0.2466 | 0.2687 |
|
| 91 |
+
| 0.6264 | 26.6187 | 14800 | 0.2487 | 0.2675 |
|
| 92 |
+
| 0.6607 | 27.3381 | 15200 | 0.2496 | 0.2683 |
|
| 93 |
+
| 0.6365 | 28.0576 | 15600 | 0.2483 | 0.2682 |
|
| 94 |
+
| 0.6374 | 28.7770 | 16000 | 0.2497 | 0.2682 |
|
| 95 |
+
| 0.6213 | 29.4964 | 16400 | 0.2496 | 0.2682 |
|
| 96 |
|
| 97 |
|
| 98 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262069880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85903b78dd64630cf7904b549287d8c9f7b6105334add90cbde4d88b4b9417aa
|
| 3 |
size 1262069880
|
runs/May04_03-51-37_Lydia/events.out.tfevents.1777884737.Lydia.20124.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9deb2e0bc5c59d37145102197721dc11bc5d4e4a1d33aba9c7bc64b6c70bfa6c
|
| 3 |
+
size 28810
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0607253dde7866fd7d219477cd83f5e75af6e16064b9f3272b9abdd30c395a7
|
| 3 |
size 5905
|