Julien Simon
commited on
Commit
•
2559184
1
Parent(s):
81cabbe
Update README.md
Browse files
README.md
CHANGED
@@ -25,30 +25,31 @@ model-index:
|
|
25 |
|
26 |
# wav2vec2-conformer-rel-pos-large-finetuned-speech-commands
|
27 |
|
28 |
-
This model is a fine-tuned version of [facebook/wav2vec2-conformer-rel-pos-large](https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large) on the speech_commands dataset.
|
29 |
-
|
30 |
-
|
31 |
-
It has been trained for 10 epochs on the [speech_commands](https://huggingface.co/datasets/speech_commands) dataset:
|
32 |
-
- subset v0.02
|
33 |
-
- full training set
|
34 |
-
- full validation set
|
35 |
|
36 |
It achieves the following results on the evaluation set:
|
37 |
- Loss: 0.5245
|
38 |
- Accuracy: 0.9724
|
39 |
|
40 |
-
|
41 |
|
|
|
42 |
|
43 |
-
|
44 |
|
45 |
The model can spot one of the following keywords: "Yes", "No", "Up", "Down", "Left", "Right", "On", "Off", "Stop", "Go", "Zero", "One", "Two", "Three", "Four", "Five", "Six", "Seven", "Eight", "Nine", "Bed", "Bird", "Cat", "Dog", "Happy", "House", "Marvin", "Sheila", "Tree", "Wow", "Backward", "Forward", "Follow", "Learn", "Visual".
|
46 |
|
47 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
-
|
50 |
|
51 |
-
###
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 3e-05
|
|
|
25 |
|
26 |
# wav2vec2-conformer-rel-pos-large-finetuned-speech-commands
|
27 |
|
28 |
+
This model is a fine-tuned version of [facebook/wav2vec2-conformer-rel-pos-large](https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large) on the [speech_commands](https://huggingface.co/datasets/speech_commands) dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
|
30 |
It achieves the following results on the evaluation set:
|
31 |
- Loss: 0.5245
|
32 |
- Accuracy: 0.9724
|
33 |
|
34 |
+
### Model description
|
35 |
|
36 |
+
TBD
|
37 |
|
38 |
+
#### Intended uses & limitations
|
39 |
|
40 |
The model can spot one of the following keywords: "Yes", "No", "Up", "Down", "Left", "Right", "On", "Off", "Stop", "Go", "Zero", "One", "Two", "Three", "Four", "Five", "Six", "Seven", "Eight", "Nine", "Bed", "Bird", "Cat", "Dog", "Happy", "House", "Marvin", "Sheila", "Tree", "Wow", "Backward", "Forward", "Follow", "Learn", "Visual".
|
41 |
|
42 |
+
### Training and evaluation data
|
43 |
+
|
44 |
+
- subset v0.02
|
45 |
+
- full training set
|
46 |
+
- full validation set
|
47 |
+
|
48 |
+
### Training procedure
|
49 |
|
50 |
+
TBD
|
51 |
|
52 |
+
###Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 3e-05
|