How to use moonshotai/Kimi-Audio-7B-Instruct with KimiAudio:
# Example usage for KimiAudio # pip install git+https://github.com/MoonshotAI/Kimi-Audio.git from kimia_infer.api.kimia import KimiAudio model = KimiAudio(model_path="moonshotai/Kimi-Audio-7B-Instruct", load_detokenizer=True) sampling_params = { "audio_temperature": 0.8, "audio_top_k": 10, "text_temperature": 0.0, "text_top_k": 5, } # For ASR asr_audio = "asr_example.wav" messages_asr = [ {"role": "user", "message_type": "text", "content": "Please transcribe the following audio:"}, {"role": "user", "message_type": "audio", "content": asr_audio} ] _, text = model.generate(messages_asr, **sampling_params, output_type="text") print(text) # For Q&A qa_audio = "qa_example.wav" messages_conv = [{"role": "user", "message_type": "audio", "content": qa_audio}] wav, text = model.generate(messages_conv, **sampling_params, output_type="both") sf.write("output_audio.wav", wav.cpu().view(-1).numpy(), 24000) print(text)
Free studio vocal data for Kimi Audio vocal pipeline benchmarking
· Sign up or log in to comment
