update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-base.en
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- marsyas/gtzan
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: whisper-base.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: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.88
|
| 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-base.en-finetuned-gtzan
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the GTZAN dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6266
|
| 36 |
+
- Accuracy: 0.88
|
| 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: 5e-05
|
| 56 |
+
- train_batch_size: 12
|
| 57 |
+
- eval_batch_size: 12
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 62 |
+
- num_epochs: 18
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 1.7396 | 1.0 | 75 | 1.6061 | 0.56 |
|
| 69 |
+
| 0.8839 | 2.0 | 150 | 0.8286 | 0.77 |
|
| 70 |
+
| 0.7631 | 3.0 | 225 | 0.6353 | 0.81 |
|
| 71 |
+
| 0.4049 | 4.0 | 300 | 0.5840 | 0.82 |
|
| 72 |
+
| 0.3031 | 5.0 | 375 | 0.4069 | 0.88 |
|
| 73 |
+
| 0.3031 | 6.0 | 450 | 0.7152 | 0.81 |
|
| 74 |
+
| 0.2879 | 7.0 | 525 | 0.7061 | 0.85 |
|
| 75 |
+
| 0.0301 | 8.0 | 600 | 0.5691 | 0.89 |
|
| 76 |
+
| 0.0311 | 9.0 | 675 | 0.6153 | 0.88 |
|
| 77 |
+
| 0.0025 | 10.0 | 750 | 0.5463 | 0.88 |
|
| 78 |
+
| 0.0036 | 11.0 | 825 | 0.6017 | 0.89 |
|
| 79 |
+
| 0.0016 | 12.0 | 900 | 0.6859 | 0.85 |
|
| 80 |
+
| 0.0014 | 13.0 | 975 | 0.5887 | 0.89 |
|
| 81 |
+
| 0.0012 | 14.0 | 1050 | 0.6525 | 0.9 |
|
| 82 |
+
| 0.0011 | 15.0 | 1125 | 0.6289 | 0.89 |
|
| 83 |
+
| 0.0011 | 16.0 | 1200 | 0.6277 | 0.88 |
|
| 84 |
+
| 0.001 | 17.0 | 1275 | 0.6274 | 0.88 |
|
| 85 |
+
| 0.0611 | 18.0 | 1350 | 0.6266 | 0.88 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.31.0
|
| 91 |
+
- Pytorch 2.0.1+cu118
|
| 92 |
+
- Datasets 2.14.3
|
| 93 |
+
- Tokenizers 0.13.3
|