End of training
Browse files- README.md +86 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- tr
|
| 5 |
+
license: mit
|
| 6 |
+
base_model: openai/whisper-large-v3-turbo
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- khanacademy
|
| 11 |
+
- turkish
|
| 12 |
+
- stem
|
| 13 |
+
- asr
|
| 14 |
+
metrics:
|
| 15 |
+
- wer
|
| 16 |
+
model-index:
|
| 17 |
+
- name: whisper-khanacademy-large-v3-turbo-tr
|
| 18 |
+
results:
|
| 19 |
+
- task:
|
| 20 |
+
name: Automatic Speech Recognition
|
| 21 |
+
type: automatic-speech-recognition
|
| 22 |
+
dataset:
|
| 23 |
+
name: ysdede/khanacademy-turkish
|
| 24 |
+
type: khanacademy
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 15.695132614398135
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
+
|
| 34 |
+
# whisper-khanacademy-large-v3-turbo-tr
|
| 35 |
+
|
| 36 |
+
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the ysdede/khanacademy-turkish dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.2129
|
| 39 |
+
- Wer: 15.6951
|
| 40 |
+
|
| 41 |
+
## Model description
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Intended uses & limitations
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training and evaluation data
|
| 50 |
+
|
| 51 |
+
More information needed
|
| 52 |
+
|
| 53 |
+
## Training procedure
|
| 54 |
+
|
| 55 |
+
### Training hyperparameters
|
| 56 |
+
|
| 57 |
+
The following hyperparameters were used during training:
|
| 58 |
+
- learning_rate: 5e-06
|
| 59 |
+
- train_batch_size: 64
|
| 60 |
+
- eval_batch_size: 32
|
| 61 |
+
- seed: 42
|
| 62 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- lr_scheduler_warmup_ratio: 0.15
|
| 65 |
+
- training_steps: 1204
|
| 66 |
+
- mixed_precision_training: Native AMP
|
| 67 |
+
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 72 |
+
| 0.2298 | 0.1429 | 172 | 0.2418 | 16.5877 |
|
| 73 |
+
| 0.2157 | 0.2857 | 344 | 0.2255 | 15.9611 |
|
| 74 |
+
| 0.1668 | 1.0939 | 516 | 0.2227 | 15.7461 |
|
| 75 |
+
| 0.1752 | 1.2367 | 688 | 0.2159 | 15.8846 |
|
| 76 |
+
| 0.1492 | 2.0449 | 860 | 0.2187 | 15.7571 |
|
| 77 |
+
| 0.1592 | 2.1877 | 1032 | 0.2134 | 15.5421 |
|
| 78 |
+
| 0.1336 | 2.3306 | 1204 | 0.2129 | 15.6951 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.48.0.dev0
|
| 84 |
+
- Pytorch 2.5.1+cu121
|
| 85 |
+
- Datasets 3.2.0
|
| 86 |
+
- Tokenizers 0.21.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3235581408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82888459eb91009f3f26027da598ee649f368fcc2d7d73d37201357046d0b6d7
|
| 3 |
size 3235581408
|