ModelVersion
The model to use to convert speech into text.
Legacy
uses the IDOL 12.x speech-to-text models. When you choose this option you can configure custom language models and custom word databases.-
Micro
,Small
, andLarge
use a new speech-to-text algorithm that was introduced in IDOL 23.2. These provide much better accuracy than the legacy models, especially for English speech. Custom language models and custom word databases are neither required nor supported, because the vocabulary of these models is not limited by their training.- The
micro
model is the fastest of the new models, and can be used to process live streams on older or less powerful hardware than the small model. - The
small
model is recommended for processing live streams. You can also use this model if you are processing files but prefer shorter processing times than offered by the large model. - The
large
model provides maximum accuracy but requires significantly more processing time. This model is not suitable for processing live streams on current hardware.
- The
Type: | String |
Default: | Legacy |
Required: | No |
Configuration Section: | TaskName |
Example: | ModelVersion=small
|
See Also: |