End of training
Browse files- README.md +97 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: nyankole_wav2vec2-runpod-unf-large
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
[<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/mbalireshawal-makerere-university/huggingface/runs/1l4ekc0h)
|
| 17 |
+
[<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/mbalireshawal-makerere-university/huggingface/runs/1l4ekc0h)
|
| 18 |
+
[<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/mbalireshawal-makerere-university/huggingface/runs/1l4ekc0h)
|
| 19 |
+
[<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/mbalireshawal-makerere-university/huggingface/runs/1l4ekc0h)
|
| 20 |
+
[<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/mbalireshawal-makerere-university/huggingface/runs/1l4ekc0h)
|
| 21 |
+
# nyankole_wav2vec2-runpod-unf-large
|
| 22 |
+
|
| 23 |
+
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.
|
| 24 |
+
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 830.9091
|
| 26 |
+
- Wer: 0.6101
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 0.0001
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 8
|
| 48 |
+
- seed: 42
|
| 49 |
+
- gradient_accumulation_steps: 2
|
| 50 |
+
- total_train_batch_size: 32
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- num_epochs: 30
|
| 54 |
+
- mixed_precision_training: Native AMP
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 60 |
+
| 7399.694 | 1.0 | 53 | 3616.8877 | 1.0 |
|
| 61 |
+
| 7452.8927 | 2.0 | 106 | 3606.0696 | 1.0 |
|
| 62 |
+
| 7321.2547 | 3.0 | 159 | 3614.7188 | 1.0 |
|
| 63 |
+
| 7283.513 | 4.0 | 212 | 3665.7957 | 1.0 |
|
| 64 |
+
| 7260.0973 | 5.0 | 265 | 3556.3738 | 1.0 |
|
| 65 |
+
| 7184.4652 | 6.0 | 318 | 3440.7732 | 1.0 |
|
| 66 |
+
| 6526.0413 | 7.0 | 371 | 2693.0374 | 1.0 |
|
| 67 |
+
| 5025.6185 | 8.0 | 424 | 1748.6117 | 0.9985 |
|
| 68 |
+
| 3761.0044 | 9.0 | 477 | 1390.0330 | 0.8946 |
|
| 69 |
+
| 3265.3567 | 10.0 | 530 | 1185.7458 | 0.8108 |
|
| 70 |
+
| 2818.3317 | 11.0 | 583 | 1076.5151 | 0.7582 |
|
| 71 |
+
| 2666.5274 | 12.0 | 636 | 1016.1800 | 0.7206 |
|
| 72 |
+
| 2484.5062 | 13.0 | 689 | 1017.9598 | 0.7026 |
|
| 73 |
+
| 2363.0265 | 14.0 | 742 | 935.6443 | 0.6879 |
|
| 74 |
+
| 2215.8507 | 15.0 | 795 | 926.4963 | 0.6670 |
|
| 75 |
+
| 2169.1753 | 16.0 | 848 | 892.7558 | 0.6608 |
|
| 76 |
+
| 2054.9318 | 17.0 | 901 | 885.1797 | 0.6461 |
|
| 77 |
+
| 2001.906 | 18.0 | 954 | 869.5634 | 0.6369 |
|
| 78 |
+
| 2011.2323 | 19.0 | 1007 | 857.0482 | 0.6317 |
|
| 79 |
+
| 1900.8241 | 20.0 | 1060 | 855.6694 | 0.625 |
|
| 80 |
+
| 1869.7319 | 21.0 | 1113 | 842.1160 | 0.6296 |
|
| 81 |
+
| 1809.5601 | 22.0 | 1166 | 838.9195 | 0.6219 |
|
| 82 |
+
| 1828.7354 | 23.0 | 1219 | 830.1293 | 0.6198 |
|
| 83 |
+
| 1804.8732 | 24.0 | 1272 | 835.9683 | 0.6173 |
|
| 84 |
+
| 1775.2409 | 25.0 | 1325 | 831.1539 | 0.6103 |
|
| 85 |
+
| 1805.726 | 26.0 | 1378 | 831.0961 | 0.6157 |
|
| 86 |
+
| 1738.365 | 27.0 | 1431 | 831.4120 | 0.6126 |
|
| 87 |
+
| 1802.3348 | 28.0 | 1484 | 831.5934 | 0.6113 |
|
| 88 |
+
| 1806.6047 | 29.0 | 1537 | 831.4467 | 0.6101 |
|
| 89 |
+
| 1788.635 | 30.0 | 1590 | 830.9091 | 0.6101 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- Transformers 4.42.4
|
| 95 |
+
- Pytorch 2.3.1+cu121
|
| 96 |
+
- Datasets 2.20.0
|
| 97 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1261938680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b74e37895b6590d91c8e5530afba9279b8b4794a78caf203d52e96d4ad44c8a3
|
| 3 |
size 1261938680
|