EzraWilliam
commited on
Commit
•
b3f4ae0
1
Parent(s):
bcaa478
End of training
Browse files
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
base_model: facebook/wav2vec2-large-xlsr-53
|
6 |
datasets:
|
7 |
- xtreme_s
|
8 |
metrics:
|
@@ -11,8 +11,8 @@ model-index:
|
|
11 |
- name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod7
|
12 |
results:
|
13 |
- task:
|
14 |
-
type: automatic-speech-recognition
|
15 |
name: Automatic Speech Recognition
|
|
|
16 |
dataset:
|
17 |
name: xtreme_s
|
18 |
type: xtreme_s
|
@@ -20,9 +20,9 @@ model-index:
|
|
20 |
split: test
|
21 |
args: fleurs.id_id
|
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/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 1.
|
36 |
-
- Wer: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -53,35 +53,37 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.001
|
56 |
-
- train_batch_size:
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 2
|
60 |
-
- total_train_batch_size:
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 600
|
64 |
-
- num_epochs:
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
-
| Training Loss | Epoch
|
70 |
-
|
71 |
-
|
|
72 |
-
| 1.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
83 |
|
84 |
-
- Transformers 4.
|
85 |
-
- Pytorch 2.2.
|
86 |
-
- Datasets 2.
|
87 |
-
- Tokenizers 0.15.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
datasets:
|
7 |
- xtreme_s
|
8 |
metrics:
|
|
|
11 |
- name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod7
|
12 |
results:
|
13 |
- task:
|
|
|
14 |
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
dataset:
|
17 |
name: xtreme_s
|
18 |
type: xtreme_s
|
|
|
20 |
split: test
|
21 |
args: fleurs.id_id
|
22 |
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.5032929202215237
|
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/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0673
|
36 |
+
- Wer: 0.5033
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.001
|
56 |
+
- train_batch_size: 8
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 16
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 600
|
64 |
+
- num_epochs: 90
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
71 |
+
| 5.2829 | 7.79 | 300 | 2.8538 | 1.0 |
|
72 |
+
| 1.9733 | 15.58 | 600 | 0.8923 | 0.7851 |
|
73 |
+
| 0.4186 | 23.38 | 900 | 0.8297 | 0.6443 |
|
74 |
+
| 0.2077 | 31.17 | 1200 | 0.8573 | 0.6011 |
|
75 |
+
| 0.1535 | 38.96 | 1500 | 0.9490 | 0.5800 |
|
76 |
+
| 0.1163 | 46.75 | 1800 | 1.0380 | 0.5652 |
|
77 |
+
| 0.1001 | 54.55 | 2100 | 0.9354 | 0.5417 |
|
78 |
+
| 0.0845 | 62.34 | 2400 | 1.0226 | 0.5364 |
|
79 |
+
| 0.0711 | 70.13 | 2700 | 1.0799 | 0.5220 |
|
80 |
+
| 0.0588 | 77.92 | 3000 | 1.0550 | 0.5050 |
|
81 |
+
| 0.0492 | 85.71 | 3300 | 1.0673 | 0.5033 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
85 |
|
86 |
+
- Transformers 4.39.0
|
87 |
+
- Pytorch 2.2.1+cu121
|
88 |
+
- Datasets 2.18.0
|
89 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262073980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0548df6da7dc096ea6455fa41b3a2aecd297b9b2afa10c18d35974780c33b2a
|
3 |
size 1262073980
|
runs/Mar22_09-51-03_8b723128d2e2/events.out.tfevents.1711101096.8b723128d2e2.2711.0
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 sha256:186c7958a61930a226cd6768a7864514a54617da06f9aa0c5dbd6a52d0953528
|
3 |
+
size 12560
|