Lakoc commited on
Commit
99c64e8
·
verified ·
1 Parent(s): fe93b05

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -12,7 +12,7 @@ tags:
12
  - DiCoW
13
  - BUT-FIT
14
  pipeline_tag: automatic-speech-recognition
15
- license: apache-2.0
16
  datasets:
17
  - microsoft/NOTSOFAR
18
  - edinburghcstr/ami
@@ -23,6 +23,8 @@ datasets:
23
  This repository contains the **DiCoW\_v3\_MLC** model developed by [BUT Speech@FIT](https://github.com/BUTSpeechFIT) for the [MLC-SLM Challenge](https://www.nexdata.ai/competition/mlc-slm).
24
  Diarization-Conditioned Whisper (DiCoW) is a novel approach to target-speaker ASR that leverages speaker diarization outputs as conditioning information.
25
 
 
 
26
  The model is described in detail in the following papers:
27
 
28
  * 📰 **Journal paper (main DiCoW paper):** [DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition](https://authors.elsevier.com/a/1lI9m_K8BYumVY)
 
12
  - DiCoW
13
  - BUT-FIT
14
  pipeline_tag: automatic-speech-recognition
15
+ license: cc-by-4.0
16
  datasets:
17
  - microsoft/NOTSOFAR
18
  - edinburghcstr/ami
 
23
  This repository contains the **DiCoW\_v3\_MLC** model developed by [BUT Speech@FIT](https://github.com/BUTSpeechFIT) for the [MLC-SLM Challenge](https://www.nexdata.ai/competition/mlc-slm).
24
  Diarization-Conditioned Whisper (DiCoW) is a novel approach to target-speaker ASR that leverages speaker diarization outputs as conditioning information.
25
 
26
+ This model is available under the terms of CC BY 4.0. It incorporates an MIT-licensed base model and CC BY 4.0 licensed training data.
27
+
28
  The model is described in detail in the following papers:
29
 
30
  * 📰 **Journal paper (main DiCoW paper):** [DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition](https://authors.elsevier.com/a/1lI9m_K8BYumVY)