Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-medium.en
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- marsyas/gtzan
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: whisper-medium.en-finetuned-gtzan
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Audio Classification
|
| 15 |
+
type: audio-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: GTZAN
|
| 18 |
+
type: marsyas/gtzan
|
| 19 |
+
config: all
|
| 20 |
+
split: train
|
| 21 |
+
args: all
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.95
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# whisper-medium.en-finetuned-gtzan
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the GTZAN dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2885
|
| 36 |
+
- Accuracy: 0.95
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 1e-05
|
| 56 |
+
- train_batch_size: 2
|
| 57 |
+
- eval_batch_size: 2
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 8
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 16
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 70 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 71 |
+
| 1.7711 | 1.0 | 112 | 1.6556 | 0.52 |
|
| 72 |
+
| 0.5477 | 2.0 | 225 | 0.4738 | 0.85 |
|
| 73 |
+
| 0.535 | 3.0 | 337 | 0.3137 | 0.92 |
|
| 74 |
+
| 0.231 | 4.0 | 450 | 0.3613 | 0.9 |
|
| 75 |
+
| 0.1923 | 5.0 | 562 | 0.2885 | 0.95 |
|
| 76 |
+
| 0.0584 | 6.0 | 675 | 0.6531 | 0.86 |
|
| 77 |
+
| 0.1783 | 7.0 | 787 | 0.5717 | 0.9 |
|
| 78 |
+
| 0.0022 | 8.0 | 900 | 0.4205 | 0.91 |
|
| 79 |
+
| 0.1032 | 9.0 | 1012 | 0.4984 | 0.91 |
|
| 80 |
+
| 0.0011 | 10.0 | 1125 | 0.3778 | 0.94 |
|
| 81 |
+
| 0.0104 | 11.0 | 1237 | 0.3709 | 0.94 |
|
| 82 |
+
| 0.0011 | 12.0 | 1350 | 0.4564 | 0.92 |
|
| 83 |
+
| 0.0009 | 13.0 | 1462 | 0.3796 | 0.94 |
|
| 84 |
+
| 0.0008 | 14.0 | 1575 | 0.3880 | 0.94 |
|
| 85 |
+
| 0.0008 | 15.0 | 1687 | 0.3930 | 0.94 |
|
| 86 |
+
| 0.0008 | 15.93 | 1792 | 0.3955 | 0.94 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- Transformers 4.37.0.dev0
|
| 92 |
+
- Pytorch 2.1.2+cu118
|
| 93 |
+
- Datasets 2.15.0
|
| 94 |
+
- Tokenizers 0.15.0
|