Struct BackendConfig 

pub struct BackendConfig {
    pub backend: BackendType,
    pub threads: usize,
    pub gpu_enabled: bool,
    pub quantization_level: QuantizationLevel,
}

Backend-agnostic configuration for transcription Each backend interprets these generic options based on its capabilities

Fields

backend: BackendType

Backend type to use (ctranslate2, whisper_cpp, moonshine, parakeet)

threads: usize

Number of CPU threads to use for inference Backends may adjust based on their threading model

gpu_enabled: bool

Whether to enable GPU acceleration if available

• CTranslate2: CUDA support
• whisper.cpp: CUDA/Metal/Vulkan support

quantization_level: QuantizationLevel

Quantization level for model weights Backends translate this to their specific quantization formats

Trait Implementations

impl Clone for BackendConfig

fn clone(&self) -> BackendConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for BackendConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for BackendConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for BackendConfig

where BackendConfig: Default,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for BackendConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.