Update README.md
Browse files
README.md
CHANGED
|
@@ -4,9 +4,14 @@ pipeline_tag: audio-classification
|
|
| 4 |
tags:
|
| 5 |
- automatic-speech-recognition
|
| 6 |
- emotion-recognition
|
| 7 |
-
- model_hub_mixin
|
| 8 |
-
- pytorch_model_hub_mixin
|
| 9 |
- speaker-identification
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# Multitask Speech Model with Wav2Vec2
|
|
@@ -48,4 +53,4 @@ Evaluation metrics:
|
|
| 48 |
|
| 49 |
Character Error Rate (CER) for character recognition
|
| 50 |
|
| 51 |
-
Accuracy for speaker and emotion classification
|
|
|
|
| 4 |
tags:
|
| 5 |
- automatic-speech-recognition
|
| 6 |
- emotion-recognition
|
|
|
|
|
|
|
| 7 |
- speaker-identification
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
metrics:
|
| 11 |
+
- accuracy
|
| 12 |
+
base_model:
|
| 13 |
+
- facebook/wav2vec2-base
|
| 14 |
+
library_name: fairseq
|
| 15 |
---
|
| 16 |
|
| 17 |
# Multitask Speech Model with Wav2Vec2
|
|
|
|
| 53 |
|
| 54 |
Character Error Rate (CER) for character recognition
|
| 55 |
|
| 56 |
+
Accuracy for speaker and emotion classification
|