模型输出 audio 和 transcript:
audio_string = ""
for chunk in completion:
if chunk.choices:
if hasattr(chunk.choices[0].delta, "audio"):
try:
audio_string += chunk.choices[0].delta.audio["data"]
except Exception as e:
print(chunk.choices[0].delta.audio["transcript"])
else:
print(chunk.usage)
wav_bytes = base64.b64decode(audio_string)
audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
sf.write("audio_assistant_py.wav", audio_np, samplerate=24000)
第 7 、8 行:为什么把 print(chunk.choices[0].delta.audio["transcript"]) 放在 Exception 后面输出?