[Refactor] Drop direct dependency on librosa (#39079)

Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Nick Cao
2026-04-18 06:55:38 +00:00
committed by GitHub
co-authored by Claude
parent 87518c3027
commit 153ba7f0f3
13 changed files with 40 additions and 44 deletions
@@ -267,7 +267,7 @@ def run_audio(model: str, max_completion_tokens: int) -> None:
{
"type": "input_audio",
"input_audio": {
# Any format supported by librosa is supported
# Any format supported by soundfile/PyAV is supported
"data": audio_base64,
"format": "wav",
},
@@ -292,7 +292,7 @@ def run_audio(model: str, max_completion_tokens: int) -> None:
{
"type": "audio_url",
"audio_url": {
# Any format supported by librosa is supported
# Any format supported by soundfile/PyAV is supported
"url": audio_url
},
},
@@ -316,7 +316,7 @@ def run_audio(model: str, max_completion_tokens: int) -> None:
{
"type": "audio_url",
"audio_url": {
# Any format supported by librosa is supported
# Any format supported by soundfile/PyAV is supported
"url": f"data:audio/ogg;base64,{audio_base64}"
},
},
@@ -12,7 +12,6 @@ model, for example:
Requirements:
- vllm with audio support
- websockets
- librosa
- numpy
The script:
@@ -26,12 +25,12 @@ import argparse
import asyncio
import json
import librosa
import numpy as np
import pybase64 as base64
import websockets
from vllm.assets.audio import AudioAsset
from vllm.multimodal.media.audio import load_audio
def audio_to_pcm16_base64(audio_path: str) -> str:
@@ -39,7 +38,7 @@ def audio_to_pcm16_base64(audio_path: str) -> str:
Load an audio file and convert it to base64-encoded PCM16 @ 16kHz.
"""
# Load audio and resample to 16kHz mono
audio, _ = librosa.load(audio_path, sr=16000, mono=True)
audio, _ = load_audio(audio_path, sr=16000, mono=True)
# Convert to PCM16
pcm16 = (audio * 32767).astype(np.int16)
# Encode as base64