Substitutions
Substitution rules contain lists of “target:replacement” mappings, which enable you to correct consistent and frequent transcription errors that result from out-of-vocabulary words, excess noise in the audio, poor enunciation, or strong accents. They can also be used to correct word combinations that rarely occur in general speech but occur frequently within a specific domain or company.
For example, useful substitutions in the insurance domain could include “giant whale : giant hail” and “hit a beer : hit a deer”.
Name |
Availability |
Values |
Description |
---|---|---|---|
subst |
V‑Blaze 7.1+ V‑Cloud 1.6+ |
true, false (default), none |
The
Note:
subst does not affect substitutions requested with the subst_list or subst_rules parameters.This parameter is intended for debugging purposes only and should not be used in production. |
substinfo |
V‑Blaze 7.1+ V‑Cloud 1.6+ |
true, false (default) |
Provides substitution details in JSON transcripts. Set In addition to the top-level JSON object, This parameter is intended for debugging purposes only and should not be used in production. Tip: The information provided by the
substinfo parameter is especially helpful for developing and debugging substitution configurations. |
subst_rules |
V‑Cloud, V‑Blaze v5.6+, V‑Spark |
string/filename |
Specifies a newline-delimited string that contains substitution rules to be applied during transcription. Rules can be specified directly as a string, however, the recommended approach is to auto-populate the string with the contents of a substitutions file. This approach makes it easier to edit and maintain these rules over time. If you are using cURL, you can specify a file for the
Note: Refer to Best practices for more detailed examples of substitution rules.
|