update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- marsyas/gtzan
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: distil-whisper-large-v2-8-ls-finetuned-gtzan
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# distil-whisper-large-v2-8-ls-finetuned-gtzan
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [rsonavane/distil-whisper-large-v2-8-ls](https://huggingface.co/rsonavane/distil-whisper-large-v2-8-ls) on the GTZAN dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4346
|
| 21 |
+
- Accuracy: 0.91
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 0.7999 | 1.0 | 112 | 1.0678 | 0.6 |
|
| 56 |
+
| 0.7487 | 1.99 | 224 | 0.8678 | 0.7 |
|
| 57 |
+
| 0.4251 | 3.0 | 337 | 1.0246 | 0.65 |
|
| 58 |
+
| 0.081 | 4.0 | 449 | 0.4755 | 0.87 |
|
| 59 |
+
| 0.0487 | 4.99 | 561 | 0.5131 | 0.89 |
|
| 60 |
+
| 0.0027 | 6.0 | 674 | 0.4820 | 0.88 |
|
| 61 |
+
| 0.002 | 6.99 | 786 | 0.4103 | 0.91 |
|
| 62 |
+
| 0.0017 | 8.0 | 899 | 0.4562 | 0.92 |
|
| 63 |
+
| 0.0019 | 9.0 | 1011 | 0.4374 | 0.91 |
|
| 64 |
+
| 0.0011 | 9.97 | 1120 | 0.4346 | 0.91 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.30.2
|
| 70 |
+
- Pytorch 2.0.1+cu118
|
| 71 |
+
- Datasets 2.13.1
|
| 72 |
+
- Tokenizers 0.13.3
|