vm6eji6m4/whisper-chinese-pro-cert

Court-grade Traditional Chinese ASR — Mandarin/Taiwanese/Hakka, word-level alignment, speaker diarization, optional three-engine certification with confidence index. 210k-term MOE lexicon.

Public
0 runs

Run vm6eji6m4/whisper-chinese-pro-cert with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
file
string
音檔或影片(mp3/mp4/m4a/wav)。也可用 file_url。
file_url
string
或提供音訊 URL。
language
None
auto
語言:auto/zh/zh-tw/zh-hk/en/ja/ko
num_speakers
integer
0

Max: 32

已知說話人數(0=自動)。
enable_diarization
boolean
True
輸出 speaker 標籤。
enable_certification
boolean
False
★ 認證版:跑第二引擎做 cross-validate(disputed/agreement)。會增加 ~80% 時間。
hotwords
string
自訂熱詞(會加入內建詞庫 prompt)。
hf_token
string
HuggingFace token(pyannote 必需)。

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "object",
  "title": "Output"
}