update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-large-xlsr-53_toy_train_data_masked_audio
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-large-xlsr-53_toy_train_data_masked_audio
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.6445
|
| 18 |
+
- Wer: 0.4938
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 16
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 52 |
+
| 3.3761 | 1.05 | 250 | 3.4022 | 0.9954 |
|
| 53 |
+
| 3.0858 | 2.1 | 500 | 3.4684 | 0.9954 |
|
| 54 |
+
| 2.6302 | 3.15 | 750 | 1.7989 | 0.9865 |
|
| 55 |
+
| 1.1292 | 4.2 | 1000 | 0.8558 | 0.7355 |
|
| 56 |
+
| 0.8371 | 5.25 | 1250 | 0.7319 | 0.6621 |
|
| 57 |
+
| 0.5992 | 6.3 | 1500 | 0.6848 | 0.6147 |
|
| 58 |
+
| 0.5189 | 7.35 | 1750 | 0.6522 | 0.5742 |
|
| 59 |
+
| 0.454 | 8.4 | 2000 | 0.6601 | 0.5531 |
|
| 60 |
+
| 0.3896 | 9.45 | 2250 | 0.6138 | 0.5439 |
|
| 61 |
+
| 0.3678 | 10.5 | 2500 | 0.6436 | 0.5320 |
|
| 62 |
+
| 0.3232 | 11.55 | 2750 | 0.5920 | 0.5174 |
|
| 63 |
+
| 0.2926 | 12.6 | 3000 | 0.6615 | 0.5107 |
|
| 64 |
+
| 0.3041 | 13.65 | 3250 | 0.6311 | 0.5015 |
|
| 65 |
+
| 0.2882 | 14.7 | 3500 | 0.6182 | 0.5004 |
|
| 66 |
+
| 0.2868 | 15.75 | 3750 | 0.6266 | 0.4943 |
|
| 67 |
+
| 0.2508 | 16.81 | 4000 | 0.6587 | 0.4965 |
|
| 68 |
+
| 0.2563 | 17.86 | 4250 | 0.6634 | 0.4939 |
|
| 69 |
+
| 0.2213 | 18.91 | 4500 | 0.6441 | 0.4925 |
|
| 70 |
+
| 0.2255 | 19.96 | 4750 | 0.6445 | 0.4938 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.17.0
|
| 76 |
+
- Pytorch 1.11.0+cu102
|
| 77 |
+
- Datasets 2.0.0
|
| 78 |
+
- Tokenizers 0.11.6
|