Commit
•
919eae7
1
Parent(s):
59866d1
End of training
Browse files
README.md
CHANGED
|
@@ -5,24 +5,9 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- marsyas/gtzan
|
| 8 |
-
metrics:
|
| 9 |
-
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: whisper-base-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: 0.62
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the GTZAN dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
-
|
| 36 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -61,27 +51,6 @@ The following hyperparameters were used during training:
|
|
| 61 |
- lr_scheduler_warmup_ratio: 0.1
|
| 62 |
- num_epochs: 15
|
| 63 |
|
| 64 |
-
### Training results
|
| 65 |
-
|
| 66 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
-
| 2.3583 | 1.0 | 113 | 2.2859 | 0.15 |
|
| 69 |
-
| 2.1906 | 2.0 | 226 | 1.9363 | 0.2 |
|
| 70 |
-
| 1.8283 | 3.0 | 339 | 1.8337 | 0.34 |
|
| 71 |
-
| 1.7248 | 4.0 | 452 | 1.7319 | 0.42 |
|
| 72 |
-
| 1.7483 | 5.0 | 565 | 1.7426 | 0.26 |
|
| 73 |
-
| 1.7937 | 6.0 | 678 | 1.7828 | 0.32 |
|
| 74 |
-
| 1.7805 | 7.0 | 791 | 1.4825 | 0.41 |
|
| 75 |
-
| 1.5479 | 8.0 | 904 | 1.3502 | 0.44 |
|
| 76 |
-
| 1.0357 | 9.0 | 1017 | 1.3520 | 0.5 |
|
| 77 |
-
| 1.4429 | 10.0 | 1130 | 1.3095 | 0.59 |
|
| 78 |
-
| 1.2226 | 11.0 | 1243 | 1.2061 | 0.58 |
|
| 79 |
-
| 0.7765 | 12.0 | 1356 | 1.2895 | 0.6 |
|
| 80 |
-
| 0.5552 | 13.0 | 1469 | 1.1772 | 0.65 |
|
| 81 |
-
| 0.3141 | 14.0 | 1582 | 1.3492 | 0.62 |
|
| 82 |
-
| 0.2403 | 15.0 | 1695 | 1.4331 | 0.62 |
|
| 83 |
-
|
| 84 |
-
|
| 85 |
### Framework versions
|
| 86 |
|
| 87 |
- Transformers 4.32.1
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- marsyas/gtzan
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: whisper-base-finetuned-gtzan
|
| 10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the GTZAN dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- eval_loss: 1.1772
|
| 21 |
+
- eval_accuracy: 0.65
|
| 22 |
+
- eval_runtime: 13.8087
|
| 23 |
+
- eval_samples_per_second: 7.242
|
| 24 |
+
- eval_steps_per_second: 0.941
|
| 25 |
+
- epoch: 4.0
|
| 26 |
+
- step: 452
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 51 |
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
- num_epochs: 15
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.32.1
|