End of training
Browse files- README.md +83 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: facebook/wav2vec2-large-uralic-voxpopuli-v2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: w2v2-large-uralic-voxpopuli-v2-karelian-cs-w-rus
|
| 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 |
+
# w2v2-large-uralic-voxpopuli-v2-karelian-cs-w-rus
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-uralic-voxpopuli-v2](https://huggingface.co/facebook/wav2vec2-large-uralic-voxpopuli-v2) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5997
|
| 21 |
+
- Wer: 0.4401
|
| 22 |
+
- Cer: 0.1228
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0001
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 43
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- training_steps: 10000
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 6.2662 | 0.48 | 500 | 1.8324 | 0.9998 | 0.6007 |
|
| 57 |
+
| 1.032 | 0.97 | 1000 | 0.7219 | 0.6129 | 0.1779 |
|
| 58 |
+
| 0.6635 | 1.45 | 1500 | 0.6393 | 0.5535 | 0.1572 |
|
| 59 |
+
| 0.5568 | 1.94 | 2000 | 0.5816 | 0.5192 | 0.1486 |
|
| 60 |
+
| 0.4728 | 2.42 | 2500 | 0.5838 | 0.5076 | 0.1444 |
|
| 61 |
+
| 0.427 | 2.9 | 3000 | 0.5746 | 0.4915 | 0.1377 |
|
| 62 |
+
| 0.3789 | 3.39 | 3500 | 0.5658 | 0.4781 | 0.1342 |
|
| 63 |
+
| 0.3543 | 3.87 | 4000 | 0.5859 | 0.4737 | 0.1349 |
|
| 64 |
+
| 0.3223 | 4.35 | 4500 | 0.5678 | 0.4708 | 0.1327 |
|
| 65 |
+
| 0.3053 | 4.84 | 5000 | 0.5572 | 0.4652 | 0.1311 |
|
| 66 |
+
| 0.2852 | 5.32 | 5500 | 0.5768 | 0.4594 | 0.1285 |
|
| 67 |
+
| 0.2663 | 5.81 | 6000 | 0.5687 | 0.4594 | 0.1282 |
|
| 68 |
+
| 0.2585 | 6.29 | 6500 | 0.5891 | 0.4572 | 0.1280 |
|
| 69 |
+
| 0.2477 | 6.77 | 7000 | 0.5930 | 0.4524 | 0.1257 |
|
| 70 |
+
| 0.2341 | 7.26 | 7500 | 0.5841 | 0.4456 | 0.1244 |
|
| 71 |
+
| 0.2325 | 7.74 | 8000 | 0.5973 | 0.4460 | 0.1242 |
|
| 72 |
+
| 0.2195 | 8.22 | 8500 | 0.6069 | 0.4403 | 0.1234 |
|
| 73 |
+
| 0.2187 | 8.71 | 9000 | 0.5899 | 0.4390 | 0.1229 |
|
| 74 |
+
| 0.2134 | 9.19 | 9500 | 0.5944 | 0.4398 | 0.1231 |
|
| 75 |
+
| 0.2111 | 9.68 | 10000 | 0.5997 | 0.4401 | 0.1228 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.33.3
|
| 81 |
+
- Pytorch 2.5.1
|
| 82 |
+
- Datasets 2.15.0
|
| 83 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262037674
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1822b493cfba4dfb9f06c6709c2eb0323903bf07d3c52e9a4099ccd40b9b4cdf
|
| 3 |
size 1262037674
|