Commit
•
0fd6ace
1
Parent(s):
53a953f
End of training
Browse files- README.md +80 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: nguyenvulebinh/wav2vec2-base-vi
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- doof-ferb/LSVSC
|
| 9 |
+
metrics:
|
| 10 |
+
- f1
|
| 11 |
+
model-index:
|
| 12 |
+
- name: vietnamese-voice-classification-model
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Audio Classification
|
| 16 |
+
type: audio-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: LSVSC
|
| 19 |
+
type: doof-ferb/LSVSC
|
| 20 |
+
metrics:
|
| 21 |
+
- name: F1
|
| 22 |
+
type: f1
|
| 23 |
+
value: 0.9830866807610994
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# vietnamese-voice-classification-model
|
| 30 |
+
|
| 31 |
+
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi) on the LSVSC dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 0.0971
|
| 34 |
+
- F1: 0.9831
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 5e-05
|
| 54 |
+
- train_batch_size: 64
|
| 55 |
+
- eval_batch_size: 64
|
| 56 |
+
- seed: 42
|
| 57 |
+
- gradient_accumulation_steps: 4
|
| 58 |
+
- total_train_batch_size: 256
|
| 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: 5
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 67 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 68 |
+
| 0.501 | 0.9931 | 36 | 0.2733 | 0.9699 |
|
| 69 |
+
| 0.1647 | 1.9862 | 72 | 0.1368 | 0.9787 |
|
| 70 |
+
| 0.1045 | 2.9793 | 108 | 0.1080 | 0.9820 |
|
| 71 |
+
| 0.0903 | 4.0 | 145 | 0.0972 | 0.9836 |
|
| 72 |
+
| 0.1065 | 4.9655 | 180 | 0.0971 | 0.9831 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.45.1
|
| 78 |
+
- Pytorch 2.4.0
|
| 79 |
+
- Datasets 3.0.1
|
| 80 |
+
- Tokenizers 0.20.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 378302360
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f65d08a2acb58b7f5e3d6a08071d63346fbd4954660873b76b8700f8d9661324
|
| 3 |
size 378302360
|