Struct SpeechModelBuilder 

pub struct SpeechModelBuilder { /* private fields */ }

Configure a text model with the various parameters for loading, running, and other inference behaviors.

Implementations

impl SpeechModelBuilder

pub fn new(model_id: impl ToString, loader_type: SpeechLoaderType) -> Self

A few defaults are applied here:

• Token source is from the cache (.cache/huggingface/token)
• Maximum number of sequences running is 32

pub fn with_dac_model_id(self, dac_model_id: String) -> Self

DAC Model ID to load from. If not provided, this is automatically downloaded from the default path for the model. This may be a HF hub repo or a local path.

pub fn with_dtype(self, dtype: ModelDType) -> Self

Load the model in a certain dtype.

pub fn with_force_cpu(self) -> Self

Force usage of the CPU device. Do not use PagedAttention with this.

pub fn with_token_source(self, token_source: TokenSource) -> Self

Source of the Hugging Face token.

pub fn with_hf_revision(self, revision: impl ToString) -> Self

Set the revision to use for a Hugging Face remote model.

pub fn with_max_num_seqs(self, max_num_seqs: usize) -> Self

Set the maximum number of sequences which can be run at once.

pub fn with_logging(self) -> Self

Enable logging.

pub async fn build(self) -> Result<Model>

Trait Implementations

impl From<SpeechModelBuilder> for AnyModelBuilder

fn from(b: SpeechModelBuilder) -> Self

Converts to this type from the input type.