-
Notifications
You must be signed in to change notification settings - Fork 69
Fix Speech to Text streaming mode #741
Copy link
Copy link
Labels
P0Most urgent fixesMost urgent fixesimportant ❗This issue has high priorityThis issue has high priorityimprovementPRs or issues focused on improvements in the current codebasePRs or issues focused on improvements in the current codebasemodelIssues related to exporting, improving, fixing ML modelsIssues related to exporting, improving, fixing ML models
Metadata
Metadata
Assignees
Labels
P0Most urgent fixesMost urgent fixesimportant ❗This issue has high priorityThis issue has high priorityimprovementPRs or issues focused on improvements in the current codebasePRs or issues focused on improvements in the current codebasemodelIssues related to exporting, improving, fixing ML modelsIssues related to exporting, improving, fixing ML models
Problem description
There is some underlying issue with Speech To Text streaming mode, which causes it to not work properly in some use cases and/or on some devices. The issue is most likely caused by the native implementation, but problems with Whisper model cannot be ruled out.
What should be done
Benefits to React Native ExecuTorch
The issue is a potential blocker for many future tasks and projects involving real-time speech to text processing, such as #553 or many demo apps.