Commit
•
871e2a0
1
Parent(s):
203c63b
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: hughlan1214/SER_wav2vec2-large-xlsr-53_240304_fin-tuned
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- f1
|
| 11 |
+
model-index:
|
| 12 |
+
- name: SER_wav2vec2-large-xlsr-53_240304_fin-tuned_2
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# SER_wav2vec2-large-xlsr-53_240304_fin-tuned_2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [hughlan1214/SER_wav2vec2-large-xlsr-53_240304_fin-tuned](https://huggingface.co/hughlan1214/SER_wav2vec2-large-xlsr-53_240304_fin-tuned) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0601
|
| 24 |
+
- Accuracy: 0.6731
|
| 25 |
+
- Precision: 0.6761
|
| 26 |
+
- Recall: 0.6794
|
| 27 |
+
- F1: 0.6738
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 4
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 10
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 59 |
+
| 0.8904 | 1.0 | 1048 | 1.1923 | 0.5773 | 0.6162 | 0.5563 | 0.5494 |
|
| 60 |
+
| 1.1394 | 2.0 | 2096 | 1.0143 | 0.6071 | 0.6481 | 0.6189 | 0.6057 |
|
| 61 |
+
| 0.9373 | 3.0 | 3144 | 1.0585 | 0.6126 | 0.6296 | 0.6254 | 0.6119 |
|
| 62 |
+
| 0.7405 | 4.0 | 4192 | 0.9580 | 0.6514 | 0.6732 | 0.6562 | 0.6576 |
|
| 63 |
+
| 1.1638 | 5.0 | 5240 | 0.9940 | 0.6486 | 0.6485 | 0.6627 | 0.6435 |
|
| 64 |
+
| 0.6741 | 6.0 | 6288 | 1.0307 | 0.6628 | 0.6710 | 0.6711 | 0.6646 |
|
| 65 |
+
| 0.604 | 7.0 | 7336 | 1.0248 | 0.6667 | 0.6678 | 0.6751 | 0.6682 |
|
| 66 |
+
| 0.6835 | 8.0 | 8384 | 1.0396 | 0.6722 | 0.6803 | 0.6790 | 0.6743 |
|
| 67 |
+
| 0.5421 | 9.0 | 9432 | 1.0493 | 0.6714 | 0.6765 | 0.6785 | 0.6736 |
|
| 68 |
+
| 0.5728 | 10.0 | 10480 | 1.0601 | 0.6731 | 0.6761 | 0.6794 | 0.6738 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.38.1
|
| 74 |
+
- Pytorch 2.2.1
|
| 75 |
+
- Datasets 2.17.1
|
| 76 |
+
- Tokenizers 0.15.2
|