End of training
Browse files- README.md +8 -6
- config.json +2 -1
- pytorch_model.bin +2 -2
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,7 +1,10 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: wav2vec2_batangueno
|
7 |
results: []
|
@@ -14,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
-
- Wer: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -42,19 +45,18 @@ The following hyperparameters were used during training:
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 1000
|
44 |
- num_epochs: 30
|
45 |
-
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
51 |
-
| 3.
|
52 |
-
| 0.
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- Transformers 4.
|
58 |
- Pytorch 2.0.1+cu118
|
59 |
- Datasets 1.18.3
|
60 |
- Tokenizers 0.14.1
|
|
|
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: wav2vec2_batangueno
|
10 |
results: []
|
|
|
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: 0.5957
|
21 |
+
- Wer: 0.3902
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 1000
|
47 |
- num_epochs: 30
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| 3.665 | 10.64 | 500 | 2.2443 | 1.0 |
|
54 |
+
| 0.6541 | 21.28 | 1000 | 0.5957 | 0.3902 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
+
- Transformers 4.34.0
|
60 |
- Pytorch 2.0.1+cu118
|
61 |
- Datasets 1.18.3
|
62 |
- Tokenizers 0.14.1
|
config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
|
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
6 |
"add_adapter": false,
|
@@ -110,7 +111,7 @@
|
|
110 |
1
|
111 |
],
|
112 |
"torch_dtype": "float32",
|
113 |
-
"transformers_version": "4.
|
114 |
"use_weighted_layer_sum": false,
|
115 |
"vocab_size": 32,
|
116 |
"xvector_output_dim": 512
|
|
|
1 |
{
|
2 |
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
+
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
6 |
"adapter_stride": 2,
|
7 |
"add_adapter": false,
|
|
|
111 |
1
|
112 |
],
|
113 |
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.34.0",
|
115 |
"use_weighted_layer_sum": false,
|
116 |
"vocab_size": 32,
|
117 |
"xvector_output_dim": 512
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:905698b4212676e5dfed35f08faebb0b9879fcda0e7b4651139a750df444f6f5
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d65fe8a0dc33835ece082264d2a8ae74efb531789b574f42fd9cee8fa5802b7c
|
3 |
+
size 4091
|