Expand description
A safe wrapper around the Coqui STT API
Typically, to use this,
- start by creating a
Model
, - if you have a scorer to load, call
enable_external_scorer
, - then call
speech_to_text
to run the algorithm.
§Features
No features are enabled by default.
raw-bindings
: exposes thecoqui-stt-sys
crate at the root under the same name.
Structs§
- Candidate
Transcript - A single transcript computed by the model, including a confidence value and the metadata for its constituent tokens.
- Metadata
- An array of
CandidateTranscript
objects computed by the model. - Model
- A trained Coqui STT model.
- Owned
Candidate Transcript - An owned variant of
CandidateTranscript
. - Owned
Metadata - An owned variant of
Metadata
. - Owned
Token Metadata - An owned variant of
TokenMetadata
. - Stream
- Streaming inference state.
- Token
Metadata - Stores text of an individual token, along with its timing information.
Enums§
- Error
- All possible errors returned by the C API plus some Rust errors.