Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- automatic-speech-recognition
|
| 5 |
+
- gary109/AI_Light_Dance
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4089
|
| 20 |
+
- Wer: 0.6472
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 10.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 0.5255 | 1.0 | 753 | 0.5928 | 0.9878 |
|
| 56 |
+
| 0.4897 | 2.0 | 1506 | 0.5564 | 0.9878 |
|
| 57 |
+
| 0.4926 | 3.0 | 2259 | 0.5204 | 0.9852 |
|
| 58 |
+
| 0.4533 | 4.0 | 3012 | 0.5061 | 0.9637 |
|
| 59 |
+
| 0.3557 | 5.0 | 3765 | 0.4360 | 0.6618 |
|
| 60 |
+
| 0.314 | 6.0 | 4518 | 0.4089 | 0.6472 |
|
| 61 |
+
| 0.284 | 7.0 | 5271 | 0.4130 | 0.5322 |
|
| 62 |
+
| 0.2762 | 8.0 | 6024 | 0.4108 | 0.5005 |
|
| 63 |
+
| 0.2646 | 9.0 | 6777 | 0.4176 | 0.4966 |
|
| 64 |
+
| 0.2637 | 10.0 | 7530 | 0.4158 | 0.4998 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.20.0.dev0
|
| 70 |
+
- Pytorch 1.9.1+cu102
|
| 71 |
+
- Datasets 2.3.3.dev0
|
| 72 |
+
- Tokenizers 0.12.1
|