biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Remove librosa from audio dependency (#37058)

Browse Source 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Isotr0py
2026-03-21 11:36:15 +08:00
committed by GitHub
parent 1c472f8fe1
commit c7f98b4d0a
18 changed files with 247 additions and 188 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
vllm/entrypoints/openai/speech_to_text/speech_to_text.py
View File

@@ -42,32 +42,13 @@ from vllm.inputs import EncoderDecoderInputs, ProcessorInputs
from vllm.logger import init_logger
from vllm.logprobs import FlatLogprobs, Logprob
from vllm.model_executor.models import SupportsTranscription
from vllm.multimodal.audio import split_audio
from vllm.multimodal.media.audio import extract_audio_from_video_bytes
from vllm.multimodal.audio import get_audio_duration, split_audio
from vllm.multimodal.media.audio import load_audio
from vllm.outputs import RequestOutput
from vllm.renderers.inputs import DictPrompt, EncoderDecoderDictPrompt
from vllm.renderers.inputs.preprocess import parse_enc_dec_prompt, parse_model_prompt
from vllm.sampling_params import BeamSearchParams, SamplingParams
from vllm.tokenizers import get_tokenizer
from vllm.utils.import_utils import PlaceholderModule
try:
import librosa
except ImportError:
librosa = PlaceholderModule("librosa") # type: ignore[assignment]
try:
import soundfile as sf
except ImportError:
sf = PlaceholderModule("soundfile") # type: ignore[assignment]
# Public libsndfile error codes exposed via `soundfile.LibsndfileError.code`, soundfile
# being librosa's main backend. Used to validate if an audio loading error is due to a
# server error vs a client error (invalid audio file).
# 1 = unrecognised format (file is not a supported audio container)
# 3 = malformed file (corrupt or structurally invalid audio)
# 4 = unsupported encoding (codec not supported by this libsndfile build)
_BAD_SF_CODES = {1, 3, 4}
SpeechToTextResponse: TypeAlias = TranscriptionResponse | TranslationResponse
SpeechToTextResponseVerbose: TypeAlias = (
@@ -214,32 +195,13 @@ class OpenAISpeechToText(OpenAIServing):
# pre-requisite for chunking, as it assumes Whisper SR.
try:
with io.BytesIO(audio_data) as buf:
y, sr = librosa.load(buf, sr=self.asr_config.sample_rate) # type: ignore[return-value]
except sf.LibsndfileError as exc:
# Only fall back for known format-detection failures.
# Re-raise anything else (e.g. corrupt but recognised format).
if exc.code not in _BAD_SF_CODES:
raise
logger.debug(
"librosa/soundfile could not decode audio from BytesIO "
"(code=%s: %s); falling back to pyav in-process decode",
exc.code,
exc,
)
try:
native_y, native_sr = extract_audio_from_video_bytes(audio_data)
sr = self.asr_config.sample_rate
y = librosa.resample(native_y, orig_sr=native_sr, target_sr=sr)
except Exception as pyav_exc:
logger.debug(
"pyAV fallback also failed: %s",
pyav_exc,
)
raise ValueError("Invalid or unsupported audio file.") from pyav_exc
y, sr = load_audio(buf, sr=self.asr_config.sample_rate)
except Exception as exc:
raise ValueError("Invalid or unsupported audio file.") from exc
duration = librosa.get_duration(y=y, sr=sr)
do_split_audio = (
self.asr_config.allow_audio_chunking
duration = get_audio_duration(y=y, sr=sr)
do_split_audio = self.asr_config.allow_audio_chunking and (
self.asr_config.max_audio_clip_s is not None
and duration > self.asr_config.max_audio_clip_s
)