End of training
Browse files- README.md +18 -11
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- common_voice_16_1
|
7 |
metrics:
|
8 |
- wer
|
9 |
-
base_model: facebook/w2v-bert-2.0
|
10 |
model-index:
|
11 |
- name: w2v-bert-2.0-sr
|
12 |
results:
|
13 |
- task:
|
14 |
-
type: automatic-speech-recognition
|
15 |
name: Automatic Speech Recognition
|
|
|
16 |
dataset:
|
17 |
name: common_voice_16_1
|
18 |
type: common_voice_16_1
|
@@ -20,9 +20,9 @@ model-index:
|
|
20 |
split: test
|
21 |
args: sr
|
22 |
metrics:
|
23 |
-
-
|
24 |
-
|
25 |
-
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_16_1 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Wer: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -61,16 +61,23 @@ The following hyperparameters were used during training:
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
-
- num_epochs:
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
71 |
-
| 2.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: facebook/w2v-bert-2.0
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_16_1
|
8 |
metrics:
|
9 |
- wer
|
|
|
10 |
model-index:
|
11 |
- name: w2v-bert-2.0-sr
|
12 |
results:
|
13 |
- task:
|
|
|
14 |
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
dataset:
|
17 |
name: common_voice_16_1
|
18 |
type: common_voice_16_1
|
|
|
20 |
split: test
|
21 |
args: sr
|
22 |
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.05344857999647204
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_16_1 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1469
|
36 |
+
- Wer: 0.0534
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
+
- num_epochs: 20
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
71 |
+
| 2.1994 | 1.89 | 300 | 0.1350 | 0.1078 |
|
72 |
+
| 0.2331 | 3.77 | 600 | 0.2306 | 0.1341 |
|
73 |
+
| 0.1879 | 5.66 | 900 | 0.1354 | 0.0766 |
|
74 |
+
| 0.1579 | 7.54 | 1200 | 0.1646 | 0.0958 |
|
75 |
+
| 0.1293 | 9.43 | 1500 | 0.1207 | 0.0713 |
|
76 |
+
| 0.1182 | 11.31 | 1800 | 0.1376 | 0.0737 |
|
77 |
+
| 0.1061 | 13.2 | 2100 | 0.1244 | 0.0580 |
|
78 |
+
| 0.1011 | 15.08 | 2400 | 0.1390 | 0.0602 |
|
79 |
+
| 0.0933 | 16.97 | 2700 | 0.1313 | 0.0524 |
|
80 |
+
| 0.0948 | 18.85 | 3000 | 0.1469 | 0.0534 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2422962160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eff6f28046924c27f71603cecfc42ee931bad8a35c5d9eb9ae80417504c7841
|
3 |
size 2422962160
|