diff --git a/examples/offline_inference/text_to_speech/moss_tts_nano/end2end.py b/examples/offline_inference/text_to_speech/moss_tts_nano/end2end.py index 979770865..1926bcb52 100644 --- a/examples/offline_inference/text_to_speech/moss_tts_nano/end2end.py +++ b/examples/offline_inference/text_to_speech/moss_tts_nano/end2end.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project """Offline inference example for MOSS-TTS-Nano via vLLM-Omni. Single-stage pipeline: the 0.1B AR LM and MOSS-Audio-Tokenizer-Nano codec @@ -136,21 +136,20 @@ def main(args) -> None: ) params_list = sampling_params - for stage_outputs in omni.generate(inputs, params_list): - for i, req_output in enumerate(stage_outputs): - for j, out in enumerate(req_output.outputs): - mm = out.multimodal_output - if mm is None: - print(f" [req {i}] No audio output.") - continue - audio = mm.get("audio") - sr_tensor = mm.get("sr") - if audio is None: - print(f" [req {i}] No waveform in multimodal_output.") - continue - sr = int(sr_tensor.item()) if sr_tensor is not None else 48000 - out_path = str(output_dir / f"output_{i}_{j}.wav") - save_audio(audio.cpu(), out_path, sr) + for i, req_output in enumerate(omni.generate(inputs, params_list)): + for j, out in enumerate(req_output.outputs): + mm = out.multimodal_output + if mm is None: + print(f" [req {i}] No audio output.") + continue + audio = mm.get("audio") + sr_tensor = mm.get("sr") + if audio is None: + print(f" [req {i}] No waveform in multimodal_output.") + continue + sr = int(sr_tensor.item()) if sr_tensor is not None else 48000 + out_path = str(output_dir / f"output_{i}_{j}.wav") + save_audio(audio.cpu(), out_path, sr) print("Done.")