Update readme
Browse files
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- numind/NuNER
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
pipeline_tag: zero-shot-classification
|
8 |
+
tags:
|
9 |
+
- asr
|
10 |
+
- Automatic Speech Recognition
|
11 |
+
- Whisper
|
12 |
+
- Ner
|
13 |
+
- Named entity recognition
|
14 |
+
---
|
15 |
+
|
16 |
+
# Whisper Ner
|
17 |
+
|
18 |
+
Whisper ner is an advanced model that allows joint speech transcription and entity recognition.
|
19 |
+
WhisperNER supports open-type NER, enabling recognition of diverse and evolving entities at inference.
|
20 |
+
We augment a large synthetic dataset with synthetic speech samples.
|
21 |
+
This allows us to train WhisperNER on a large number of examples with diverse NER tags.
|
22 |
+
During training, the model is prompted with NER labels and optimized to output the transcribed utterance along with the corresponding tagged entities.
|
23 |
+
|
24 |
+
---------
|
25 |
+
|
26 |
+
## Training Details
|
27 |
+
|
28 |
+
|
29 |
+
|
30 |
+
|
31 |
+
---------
|
32 |
+
|
33 |
+
## Usage
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
+
|
41 |
+
|