Skip to content

README.md

Latest commit

 

History

History
52 lines (36 loc) · 14.3 KB

README.md

File metadata and controls

52 lines (36 loc) · 14.3 KB

Container.Audio

Overview

Available Operations

transcribe

Given an audio file, the model transcribes it into text.

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.container.audio.transcribe(
        file="@/path/to/file/audio.mp3".encode(), model="(adapter-route)"
    )

    # Handle response
    print(res)

Parameters

Parameter Type Required Description Example
file bytes ✔️ The audio file object (not file name) to transcribe, in one of these formats: mp3, wav, flac, ogg, and many other standard audio formats.
model OptionalNullable[str] ➖ Routes the request to a specific adapter. (adapter-route)
chunking_strategy OptionalNullable[models.ContainerAudioTranscriptionBodyChunkingStrategy] ➖ Controls how the audio is cut into chunks. When set to "auto", the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. server_vad object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block.
language OptionalNullable[str] ➖ The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.
temperature OptionalNullable[float] ➖ The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.
server_url Optional[str] ➖ An optional server URL to use. http://localhost:8080

Response

models.ContainerAudioTranscriptionSuccess

Errors

Error Type Status Code Content Type
models.SDKError 4XX, 5XX */*