Instructions to use zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f6 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-f6 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-f6")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f6") model = AutoModelForCTC.from_pretrained("zacdan4801/wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f6", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +43 -43
- model.safetensors +1 -1
- runs/May03_23-32-44_Lydia/events.out.tfevents.1777869204.Lydia.20124.6 +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: 0.2470
|
| 20 |
+
- Per: 0.2700
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Per |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 17.6564 | 0.7194 | 400 | 4.5685 | 0.9888 |
|
| 56 |
+
| 4.3982 | 1.4388 | 800 | 4.0889 | 0.9887 |
|
| 57 |
+
| 4.078 | 2.1583 | 1200 | 3.6693 | 0.9888 |
|
| 58 |
+
| 3.3137 | 2.8777 | 1600 | 1.6025 | 0.4352 |
|
| 59 |
+
| 2.0862 | 3.5971 | 2000 | 0.8676 | 0.3350 |
|
| 60 |
+
| 1.613 | 4.3165 | 2400 | 0.6230 | 0.3078 |
|
| 61 |
+
| 1.3804 | 5.0360 | 2800 | 0.4992 | 0.2936 |
|
| 62 |
+
| 1.2312 | 5.7554 | 3200 | 0.4202 | 0.2872 |
|
| 63 |
+
| 1.1465 | 6.4748 | 3600 | 0.3793 | 0.2818 |
|
| 64 |
+
| 1.0451 | 7.1942 | 4000 | 0.3470 | 0.2783 |
|
| 65 |
+
| 0.9853 | 7.9137 | 4400 | 0.3207 | 0.2768 |
|
| 66 |
+
| 0.9449 | 8.6331 | 4800 | 0.3132 | 0.2768 |
|
| 67 |
+
| 0.8976 | 9.3525 | 5200 | 0.3061 | 0.2752 |
|
| 68 |
+
| 0.8768 | 10.0719 | 5600 | 0.2952 | 0.2755 |
|
| 69 |
+
| 0.8707 | 10.7914 | 6000 | 0.2927 | 0.2751 |
|
| 70 |
+
| 0.854 | 11.5108 | 6400 | 0.2928 | 0.2750 |
|
| 71 |
+
| 0.8301 | 12.2302 | 6800 | 0.2845 | 0.2766 |
|
| 72 |
+
| 0.8017 | 12.9496 | 7200 | 0.2830 | 0.2726 |
|
| 73 |
+
| 0.781 | 13.6691 | 7600 | 0.2815 | 0.2730 |
|
| 74 |
+
| 0.7917 | 14.3885 | 8000 | 0.2737 | 0.2723 |
|
| 75 |
+
| 0.7449 | 15.1079 | 8400 | 0.2696 | 0.2731 |
|
| 76 |
+
| 0.7606 | 15.8273 | 8800 | 0.2674 | 0.2710 |
|
| 77 |
+
| 0.7411 | 16.5468 | 9200 | 0.2634 | 0.2710 |
|
| 78 |
+
| 0.7137 | 17.2662 | 9600 | 0.2641 | 0.2728 |
|
| 79 |
+
| 0.7264 | 17.9856 | 10000 | 0.2567 | 0.2701 |
|
| 80 |
+
| 0.7062 | 18.7050 | 10400 | 0.2604 | 0.2708 |
|
| 81 |
+
| 0.6896 | 19.4245 | 10800 | 0.2568 | 0.2714 |
|
| 82 |
+
| 0.7088 | 20.1439 | 11200 | 0.2566 | 0.2703 |
|
| 83 |
+
| 0.6848 | 20.8633 | 11600 | 0.2555 | 0.2699 |
|
| 84 |
+
| 0.6857 | 21.5827 | 12000 | 0.2572 | 0.2710 |
|
| 85 |
+
| 0.6834 | 22.3022 | 12400 | 0.2563 | 0.2708 |
|
| 86 |
+
| 0.6896 | 23.0216 | 12800 | 0.2520 | 0.2700 |
|
| 87 |
+
| 0.6645 | 23.7410 | 13200 | 0.2487 | 0.2690 |
|
| 88 |
+
| 0.672 | 24.4604 | 13600 | 0.2513 | 0.2697 |
|
| 89 |
+
| 0.6551 | 25.1799 | 14000 | 0.2485 | 0.2703 |
|
| 90 |
+
| 0.6489 | 25.8993 | 14400 | 0.2501 | 0.2700 |
|
| 91 |
+
| 0.6329 | 26.6187 | 14800 | 0.2487 | 0.2697 |
|
| 92 |
+
| 0.6639 | 27.3381 | 15200 | 0.2479 | 0.2701 |
|
| 93 |
+
| 0.6385 | 28.0576 | 15600 | 0.2489 | 0.2705 |
|
| 94 |
+
| 0.6411 | 28.7770 | 16000 | 0.2473 | 0.2705 |
|
| 95 |
+
| 0.6462 | 29.4964 | 16400 | 0.2470 | 0.2700 |
|
| 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 sha256:60eda1fad1c89d950d3475e0951eab19979cae9d6371698e717ffaf9eb753d08
|
| 3 |
size 1262069880
|
runs/May03_23-32-44_Lydia/events.out.tfevents.1777869204.Lydia.20124.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f723f20aa20045e3a79e13cf63c8b7a607ef6571c763c1da0fd8ee862b851ae
|
| 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 sha256:30b0cff3ac96519962270b12a88ffe97de0f2a47d243dc437b5f12b2a1c321e2
|
| 3 |
size 5905
|