Struct WhisperMetadata

pub struct WhisperMetadata {

    pub model_name: String,
    pub model_alias: String,
    pub model_path: PathBuf,
    pub log_enable: bool,
    pub debug_log: bool,
    pub threads: u64,
    pub translate: bool,
    pub language: String,
    pub processors: u64,
    pub offset_time: u64,
    pub duration: u64,
    pub max_context: i32,
    pub max_len: u64,
    pub split_on_word: bool,
    pub output_txt: bool,
    pub output_vtt: bool,
    pub output_srt: bool,
    pub output_lrc: bool,
    pub output_csv: bool,
    pub output_json: bool,
    pub temperature: f64,
    pub detect_language: bool,
    pub prompt: Option<String>,
}

Available on crate feature whisper only.

Metadata for whisper model

Fields

model_name: String

model_alias: String

model_path: PathBuf

log_enable: bool

debug_log: bool

Enable debug mode. Defaults to false.

threads: u64

Number of threads to use during computation. Defaults to 4.

translate: bool

Translate from source language to english. Defaults to false.

language: String

The language of the input audio. auto for auto-detection. Defaults to en.

Supplying the input language in ISO-639-1 format will improve accuracy and latency.

processors: u64

Number of processors to use during computation. Defaults to 1.

offset_time: u64

Time offset in milliseconds. Defaults to 0.

duration: u64

Duration of audio to process in milliseconds. Defaults to 0.

max_context: i32

Maximum number of text context tokens to store. Defaults to -1.

max_len: u64

Maximum segment length in characters. Defaults to 0.

split_on_word: bool

Split on word rather than on token. Defaults to false.

output_txt: bool

Output result in a text file. Defaults to false.

output_vtt: bool

Output result in a vtt file. Defaults to false.

output_srt: bool

Output result in a srt file. Defaults to false.

output_lrc: bool

Output result in a lrc file. Defaults to false.

output_csv: bool

Output result in a CSV file. Defaults to false.

output_json: bool

Output result in a JSON file. Defaults to false.

temperature: f64

Sampling temperature, between 0 and 1. Defaults to 0.00.

detect_language: bool

Automatically detect the spoken language in the provided audio input.

prompt: Option<String>

Text to guide the model. The max length is n_text_ctx/2 tokens.

Trait Implementations

impl BaseMetadata for WhisperMetadata

fn model_name(&self) -> &str

fn model_alias(&self) -> &str

impl Clone for WhisperMetadata

fn clone(&self) -> WhisperMetadata

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for WhisperMetadata

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

Formats the value using the given formatter.

impl Default for WhisperMetadata

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for WhisperMetadata

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for WhisperMetadata

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

where __S: Serializer,

Serialize this value into the given Serde serializer.