End of training
Browse files- README.md +75 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: peft
|
| 6 |
+
tags:
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: openai/whisper-large-v2
|
| 9 |
+
datasets:
|
| 10 |
+
- customd_ataset
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Whisper large-v2 Korean - ML_project_custom_data_10epoch_with500
|
| 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 large-v2 Korean - ML_project_custom_data_10epoch_with500
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the customd_ataset dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.7993
|
| 24 |
+
- Cer: 20.9642
|
| 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: 0.001
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 2
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 50
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 57 |
+
| 0.1305 | 1.0 | 113 | 0.8786 | 53.5427 |
|
| 58 |
+
| 0.1204 | 2.0 | 226 | 0.8298 | 93.2067 |
|
| 59 |
+
| 0.0958 | 3.0 | 339 | 0.8469 | 24.7626 |
|
| 60 |
+
| 0.0543 | 4.0 | 452 | 0.8597 | 46.3112 |
|
| 61 |
+
| 0.0408 | 5.0 | 565 | 0.8339 | 63.3309 |
|
| 62 |
+
| 0.0375 | 6.0 | 678 | 0.8222 | 60.4091 |
|
| 63 |
+
| 0.0267 | 7.0 | 791 | 0.7989 | 20.7451 |
|
| 64 |
+
| 0.0066 | 8.0 | 904 | 0.8033 | 24.9087 |
|
| 65 |
+
| 0.0061 | 9.0 | 1017 | 0.7966 | 20.2337 |
|
| 66 |
+
| 0.0021 | 10.0 | 1130 | 0.7993 | 20.9642 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.11.2.dev0
|
| 72 |
+
- Transformers 4.41.2
|
| 73 |
+
- Pytorch 2.3.0+cu121
|
| 74 |
+
- Datasets 2.19.2
|
| 75 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 62969640
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9da04d5e2cfd016f6f77a118c453b56e5049cf3a15415efc390ffb9068ff38a
|
| 3 |
size 62969640
|