Commit
•
2645a76
1
Parent(s):
d67db95
End of training
Browse files- README.md +18 -2
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: facebook/wav2vec2-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: wav2vec2-base-nsc-demo-4
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# wav2vec2-base-nsc-demo-4
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -32,17 +37,28 @@ More information needed
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
-
- learning_rate:
|
| 36 |
- train_batch_size: 32
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 100
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
|
|
|
| 3 |
base_model: facebook/wav2vec2-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-base-nsc-demo-4
|
| 10 |
results: []
|
|
|
|
| 16 |
# wav2vec2-base-nsc-demo-4
|
| 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: 1.0598
|
| 21 |
+
- Wer: 0.5177
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 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: 100
|
| 47 |
+
- num_epochs: 200
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 2.943 | 4.55 | 100 | 2.9614 | 1.0 |
|
| 54 |
+
| 2.909 | 9.09 | 200 | 2.9454 | 1.0 |
|
| 55 |
+
| 2.8673 | 13.64 | 300 | 2.9148 | 1.0 |
|
| 56 |
+
| 2.3216 | 18.18 | 400 | 1.9129 | 0.9218 |
|
| 57 |
+
| 0.8129 | 22.73 | 500 | 1.0840 | 0.6480 |
|
| 58 |
+
| 0.3488 | 27.27 | 600 | 1.0021 | 0.5721 |
|
| 59 |
+
| 0.2166 | 31.82 | 700 | 1.0291 | 0.5568 |
|
| 60 |
+
| 0.153 | 36.36 | 800 | 1.0672 | 0.5394 |
|
| 61 |
+
| 0.1186 | 40.91 | 900 | 1.0598 | 0.5177 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377658785
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07b6f15e2a599ef5f3a33bac0d30a63d58c0bcf3b6bbfca9025e78ef4cc171cb
|
| 3 |
size 377658785
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd1e47ff5a03f8ec611ec3916f10a2bf2cb7e5a7510146586b01fc3f6e43429
|
| 3 |
size 4027
|