Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xslr-commonvoice_jsut_split
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-large-xslr-commonvoice_jsut_split
|
| 16 |
+
|
| 17 |
+
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.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5074
|
| 20 |
+
- Cer: 0.1392
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 1000
|
| 48 |
+
- num_epochs: 10
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| 9.2478 | 0.8117 | 500 | 4.3917 | 0.9903 |
|
| 56 |
+
| 8.0651 | 1.6234 | 1000 | 4.0166 | 0.9903 |
|
| 57 |
+
| 2.7888 | 2.4351 | 1500 | 1.0882 | 0.2423 |
|
| 58 |
+
| 2.7409 | 3.2468 | 2000 | 0.7290 | 0.1821 |
|
| 59 |
+
| 1.6139 | 4.0584 | 2500 | 0.6303 | 0.1644 |
|
| 60 |
+
| 1.6685 | 4.8701 | 3000 | 0.5868 | 0.1561 |
|
| 61 |
+
| 1.4885 | 5.6818 | 3500 | 0.5589 | 0.1505 |
|
| 62 |
+
| 1.8946 | 6.4935 | 4000 | 0.5399 | 0.1470 |
|
| 63 |
+
| 1.3098 | 7.3052 | 4500 | 0.5269 | 0.1431 |
|
| 64 |
+
| 1.2762 | 8.1169 | 5000 | 0.5158 | 0.1409 |
|
| 65 |
+
| 1.2075 | 8.9286 | 5500 | 0.5122 | 0.1402 |
|
| 66 |
+
| 1.5473 | 9.7403 | 6000 | 0.5074 | 0.1392 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.47.1
|
| 72 |
+
- Pytorch 2.5.1+cu121
|
| 73 |
+
- Datasets 3.2.0
|
| 74 |
+
- Tokenizers 0.21.0
|