update model card README.md
Browse files
README.md
CHANGED
@@ -4,9 +4,24 @@ tags:
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- audiofolder
|
|
|
|
|
7 |
model-index:
|
8 |
- name: wav2vec2-xlsr-53-espeak-cv-ft-bak-ntsema-colab
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,6 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# wav2vec2-xlsr-53-espeak-cv-ft-bak-ntsema-colab
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/wav2vec2-xlsr-53-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-xlsr-53-espeak-cv-ft) on the audiofolder dataset.
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -34,10 +52,10 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0003
|
37 |
-
- train_batch_size:
|
38 |
- eval_batch_size: 8
|
39 |
- seed: 42
|
40 |
-
- gradient_accumulation_steps:
|
41 |
- total_train_batch_size: 32
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
@@ -47,6 +65,11 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- audiofolder
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
model-index:
|
10 |
- name: wav2vec2-xlsr-53-espeak-cv-ft-bak-ntsema-colab
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: audiofolder
|
17 |
+
type: audiofolder
|
18 |
+
config: default
|
19 |
+
split: train
|
20 |
+
args: default
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 1.0547550432276658
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
# wav2vec2-xlsr-53-espeak-cv-ft-bak-ntsema-colab
|
31 |
|
32 |
This model is a fine-tuned version of [facebook/wav2vec2-xlsr-53-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-xlsr-53-espeak-cv-ft) on the audiofolder dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: inf
|
35 |
+
- Wer: 1.0548
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 0.0003
|
55 |
+
- train_batch_size: 4
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 8
|
59 |
- total_train_batch_size: 32
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
|
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| 3.5109 | 8.33 | 400 | inf | 1.0807 |
|
71 |
+
| 0.4252 | 16.66 | 800 | inf | 1.0519 |
|
72 |
+
| 0.1744 | 24.99 | 1200 | inf | 1.0548 |
|
73 |
|
74 |
|
75 |
### Framework versions
|