Upload 2 files
Browse files- README.md +13 -11
- training_args.bin +0 -0
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: openai/whisper-small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# whisper-small-sv
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Wer:
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -44,20 +44,22 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
|
|
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
| 59 |
|
| 60 |
-
- Transformers 4.
|
| 61 |
-
- Pytorch 2.1.0+
|
| 62 |
- Datasets 2.15.0
|
| 63 |
- Tokenizers 0.15.0
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-small.en
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 15 |
|
| 16 |
# whisper-small-sv
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6010
|
| 21 |
+
- Wer: 49.3074
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- training_steps: 4000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 54 |
+
| 0.5121 | 1.27 | 1000 | 0.6973 | 58.2803 |
|
| 55 |
+
| 0.2409 | 2.54 | 2000 | 0.5989 | 49.5818 |
|
| 56 |
+
| 0.1565 | 3.81 | 3000 | 0.5806 | 48.0991 |
|
| 57 |
+
| 0.0729 | 5.08 | 4000 | 0.6010 | 49.3074 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
| 61 |
|
| 62 |
+
- Transformers 4.37.0.dev0
|
| 63 |
+
- Pytorch 2.1.0+cu121
|
| 64 |
- Datasets 2.15.0
|
| 65 |
- Tokenizers 0.15.0
|
training_args.bin
CHANGED
|
Binary files a/training_args.bin and b/training_args.bin differ
|
|
|