End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- tr
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
base_model: openai/whisper-base
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
metrics:
|
| 10 |
+
- wer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: whisper-base
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# whisper-base
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1952
|
| 24 |
+
- Wer: 10.4439
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 1e-05
|
| 44 |
+
- train_batch_size: 32
|
| 45 |
+
- eval_batch_size: 16
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- training_steps: 60000
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|
|
| 57 |
+
| 0.2139 | 0.0833 | 5000 | 0.1884 | 16.6399 |
|
| 58 |
+
| 0.1146 | 0.1667 | 10000 | 0.1447 | 13.0148 |
|
| 59 |
+
| 0.0686 | 0.25 | 15000 | 0.1384 | 11.3586 |
|
| 60 |
+
| 0.0427 | 0.3333 | 20000 | 0.1471 | 11.4970 |
|
| 61 |
+
| 0.0274 | 0.4167 | 25000 | 0.1585 | 10.8926 |
|
| 62 |
+
| 0.0195 | 0.5 | 30000 | 0.1702 | 11.3447 |
|
| 63 |
+
| 0.0155 | 0.5833 | 35000 | 0.1773 | 10.6100 |
|
| 64 |
+
| 0.0126 | 1.0062 | 40000 | 0.1863 | 11.4255 |
|
| 65 |
+
| 0.0099 | 1.0895 | 45000 | 0.1929 | 10.6665 |
|
| 66 |
+
| 0.01 | 1.1729 | 50000 | 0.1933 | 10.6665 |
|
| 67 |
+
| 0.0085 | 1.2562 | 55000 | 0.1953 | 10.5224 |
|
| 68 |
+
| 0.0085 | 1.3395 | 60000 | 0.1952 | 10.4439 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.45.2
|
| 74 |
+
- Pytorch 2.5.1+cu121
|
| 75 |
+
- Datasets 3.2.0
|
| 76 |
+
- Tokenizers 0.20.3
|