Commit
•
80821c0
1
Parent(s):
6cbeba0
Model save
Browse files- README.md +76 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: w2v2-base-pretrained_lr1e-4_at0.3_da1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# w2v2-base-pretrained_lr1e-4_at0.3_da1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 6.0832
|
| 21 |
+
- Wer: 1.0503
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 32
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- num_epochs: 60
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 18.217 | 3.97 | 250 | 4.5592 | 1.0 |
|
| 55 |
+
| 3.272 | 7.94 | 500 | 3.7936 | 1.0 |
|
| 56 |
+
| 2.4362 | 11.9 | 750 | 2.3296 | 1.0085 |
|
| 57 |
+
| 0.4638 | 15.87 | 1000 | 3.0200 | 1.0264 |
|
| 58 |
+
| 0.2526 | 19.84 | 1250 | 3.8211 | 1.0558 |
|
| 59 |
+
| 0.1458 | 23.81 | 1500 | 4.3826 | 1.0439 |
|
| 60 |
+
| 0.0912 | 27.78 | 1750 | 4.6974 | 1.0401 |
|
| 61 |
+
| 0.0637 | 31.75 | 2000 | 5.7380 | 1.0469 |
|
| 62 |
+
| 0.0492 | 35.71 | 2250 | 5.6284 | 1.0520 |
|
| 63 |
+
| 0.0413 | 39.68 | 2500 | 5.8445 | 1.0362 |
|
| 64 |
+
| 0.031 | 43.65 | 2750 | 5.8013 | 1.0473 |
|
| 65 |
+
| 0.0248 | 47.62 | 3000 | 6.1615 | 1.0456 |
|
| 66 |
+
| 0.0228 | 51.59 | 3250 | 5.9906 | 1.0439 |
|
| 67 |
+
| 0.016 | 55.56 | 3500 | 6.1408 | 1.0494 |
|
| 68 |
+
| 0.0159 | 59.52 | 3750 | 6.0832 | 1.0503 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.35.0
|
| 74 |
+
- Pytorch 2.0.0
|
| 75 |
+
- Datasets 2.14.6
|
| 76 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377709504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32aba8e804b66f6f3c1a1007a9a79087c3af388f1d8da892f2ded1ea37e3bbc2
|
| 3 |
size 377709504
|