Speech recognition service supporting Chinese and English transcription with speaker identification. Based on Whisper architecture.
vibevoice-asr| 模型 ID | vibevoice-asr |
|---|---|
| 模型名稱 | VibeVoice ASR |
| 說明 | Speech recognition service supporting Chinese and English transcription with speaker identification. Based on Whisper architecture. |
| 相關連結 | https://huggingface.co/openai/whisper-large-v3 |
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.ithu.tw/v1",
)
response = client.chat.completions.create(
model="vibevoice-asr",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)