Unverified Commit d12d2014 authored by Isotr0py's avatar Isotr0py Committed by GitHub
Browse files

[Bugfix] Fix failing FunASR processor test (#35111)


Signed-off-by: default avatarIsotr0py <mozf@mail2.sysu.edu.cn>
parent b3ad37c5
...@@ -460,8 +460,6 @@ def test_processing_correctness( ...@@ -460,8 +460,6 @@ def test_processing_correctness(
num_batches: int, num_batches: int,
simplify_rate: float, simplify_rate: float,
): ):
if model_id == "allendou/Fun-ASR-Nano-2512-vllm":
pytest.skip("Cached audio `input_features` not matched. Fix later.")
if model_id == "google/gemma-3n-E2B-it": if model_id == "google/gemma-3n-E2B-it":
pytest.skip("Fix later") pytest.skip("Fix later")
if model_id == "OpenGVLab/InternVL2-2B": if model_id == "OpenGVLab/InternVL2-2B":
......
...@@ -361,11 +361,11 @@ class FunASRFeatureExtractor(SequenceFeatureExtractor): ...@@ -361,11 +361,11 @@ class FunASRFeatureExtractor(SequenceFeatureExtractor):
input_features = padded_inputs.get("input_features").transpose(2, 0, 1) input_features = padded_inputs.get("input_features").transpose(2, 0, 1)
self.frontend = WavFrontend(**self.frontend_conf) frontend = WavFrontend(**self.frontend_conf, dither=self.dither)
input_features, speech_lengths = self.extract_fbank( input_features, speech_lengths = self.extract_fbank(
input_features[0], input_features[0],
data_type=kwargs.get("data_type", "sound"), data_type=kwargs.get("data_type", "sound"),
frontend=self.frontend, frontend=frontend,
is_final=True, is_final=True,
) )
olens = 1 + (speech_lengths - 3 + 2 * 1) // 2 olens = 1 + (speech_lengths - 3 + 2 * 1) // 2
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment