[Frontend] Remove librosa from audio dependency (#37058)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
@@ -188,7 +188,7 @@ class FireRedASR2FeatureExtractor(SequenceFeatureExtractor):
|
||||
for speech in raw_speech:
|
||||
"""
|
||||
We must multiply by 32768 here because FireRedASR2 loads audio data
|
||||
using kaldiio.load_mat, while vLLM loads audio data using librosa.
|
||||
using kaldiio.load_mat, while vLLM loads audio data using pyav.
|
||||
"""
|
||||
speech = speech * 32768
|
||||
fbank = self.fbank(sampling_rate, speech)
|
||||
|
||||
Reference in New Issue
Block a user