End of training
Browse files- README.md +21 -10
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: whisper-small-sc
|
| 9 |
results: []
|
|
@@ -16,14 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 1028.1037
|
| 23 |
-
- eval_samples_per_second: 4.343
|
| 24 |
-
- eval_steps_per_second: 0.136
|
| 25 |
-
- epoch: 4.6012
|
| 26 |
-
- step: 750
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -42,16 +39,30 @@ More information needed
|
|
| 42 |
### Training hyperparameters
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
-
- learning_rate:
|
| 46 |
-
- train_batch_size:
|
| 47 |
- eval_batch_size: 32
|
| 48 |
- seed: 42
|
|
|
|
|
|
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 250
|
| 52 |
- training_steps: 2500
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- Transformers 4.44.2
|
|
|
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: whisper-small-sc
|
| 11 |
results: []
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2992
|
| 22 |
+
- Wer Ortho: 10.7269
|
| 23 |
+
- Wer: 10.2317
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
- eval_batch_size: 32
|
| 45 |
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_steps: 250
|
| 51 |
- training_steps: 2500
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
|
| 58 |
+
| 0.2799 | 0.7704 | 250 | 0.2614 | 12.1130 | 11.6261 |
|
| 59 |
+
| 0.1454 | 1.5408 | 500 | 0.2367 | 11.0523 | 10.6016 |
|
| 60 |
+
| 0.072 | 2.3112 | 750 | 0.2428 | 10.6736 | 10.2154 |
|
| 61 |
+
| 0.0488 | 3.0817 | 1000 | 0.2638 | 10.8335 | 10.3623 |
|
| 62 |
+
| 0.0294 | 3.8521 | 1250 | 0.2689 | 11.2821 | 10.7793 |
|
| 63 |
+
| 0.012 | 4.6225 | 1500 | 0.2992 | 10.7269 | 10.2317 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.44.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:351eea8c3feb8b58fe0119ef4a0564fb29f609a47dc34c4032fa9e37630ee7e6
|
| 3 |
size 966995080
|