Update README.md
Browse files
README.md
CHANGED
@@ -33,7 +33,7 @@ Evaluation Data
|
|
33 |
- Num. of Samples: 6,000
|
34 |
- Audio Length: 12 Hours
|
35 |
|
36 |
-
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 0.0001
|
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
|
|
48 |
- num_epochs: 20 (EarlyStopping: patience: 5 epochs max)
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
-
|
52 |
|
53 |
Phone Error Rate 3.88%
|
54 |
|
55 |
-
|
56 |
![output_examples](./output_examples.png)
|
57 |
|
58 |
-
|
59 |
|
60 |
# Vowels
|
61 |
![mfa_ipa_chart_vowels](./mfa_ipa_chart_vowels.png)
|
@@ -63,7 +63,7 @@ Phone Error Rate 3.88%
|
|
63 |
# Consonants
|
64 |
![mfa_ipa_chart_consonants](./mfa_ipa_chart_consonants.png)
|
65 |
|
66 |
-
|
67 |
|
68 |
- Transformers 4.21.3
|
69 |
- Pytorch 1.12.1
|
|
|
33 |
- Num. of Samples: 6,000
|
34 |
- Audio Length: 12 Hours
|
35 |
|
36 |
+
## Training Hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 0.0001
|
|
|
48 |
- num_epochs: 20 (EarlyStopping: patience: 5 epochs max)
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
+
## Evaluation Result
|
52 |
|
53 |
Phone Error Rate 3.88%
|
54 |
|
55 |
+
## Output Examples
|
56 |
![output_examples](./output_examples.png)
|
57 |
|
58 |
+
## MFA-IPA Phoneset Tables
|
59 |
|
60 |
# Vowels
|
61 |
![mfa_ipa_chart_vowels](./mfa_ipa_chart_vowels.png)
|
|
|
63 |
# Consonants
|
64 |
![mfa_ipa_chart_consonants](./mfa_ipa_chart_consonants.png)
|
65 |
|
66 |
+
## Framework versions
|
67 |
|
68 |
- Transformers 4.21.3
|
69 |
- Pytorch 1.12.1
|