search

Joll59 / d-ser-t

d-ser-t quantifies speech recognition accuracy of the MSFT speech service and/or user created MSFT custom speech service models.
2 stars 2 forks source link

Audio folder only #60

Closed Joll59 closed 5 years ago

Joll59 commented 5 years ago

Created a method in main.ts to handle an array of file paths, without a transcription file. It returns an Array<{count, file, transcription}> to be consumed downstream by another service. This method can only be called programmatically cannot be accessed via cli.