[Refactor] Remove resampy dependency (#2891)

Signed-off-by: Nick Cao <ncao@redhat.com>

examples/online_serving/qwen3_tts/speaker_embedding_interpolation.py

@@ -5,7 +5,7 @@ speaker encoder from a Qwen3-TTS checkpoint, then interpolates between them
 using SLERP and sends the result to the /v1/audio/speech API.
 
 Requirements:
-    pip install torch resampy soundfile numpy httpx
+    pip install torch soundfile numpy httpx
 
 Examples:
     # Extract and save an embedding
@@ -143,11 +143,12 @@ def _load_speaker_encoder_weights(encoder: torch.nn.Module, model_path: str) ->
 
 def compute_mel_spectrogram(audio: np.ndarray, sr: int = 24000) -> torch.Tensor:
     """Compute 128-bin mel spectrogram matching Qwen3-TTS's extraction pipeline."""
-    from vllm.multimodal.audio import resample_audio_resampy
+    from vllm.multimodal.audio import AudioResampler
 
     # Resample to 24kHz if needed
     if sr != 24000:
-        audio = resample_audio_resampy(audio.astype(np.float32), orig_sr=sr, target_sr=24000)
+        resampler = AudioResampler(target_sr=24000)
+        audio = resampler.resample(audio.astype(np.float32), orig_sr=sr)
 
     y = torch.from_numpy(audio).unsqueeze(0).float()
 

requirements/common.txt

@@ -1,7 +1,6 @@
 # Common dependencies for all platforms
 av>=14.0.0
 omegaconf>=2.3.0
-resampy>=0.4.3
 diffusers>=0.36.0
 accelerate==1.12.0
 soundfile>=0.13.1

vllm_omni/model_executor/models/qwen3_tts/qwen3_tts_talker.py

@@ -23,6 +23,7 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
 from vllm.model_executor.models.qwen3 import Qwen3Model
 from vllm.model_executor.models.utils import AutoWeightsLoader, PPMissingLayer, WeightsMapper, maybe_prefix
+from vllm.multimodal.audio import AudioResampler
 from vllm.sequence import IntermediateTensors
 
 from vllm_omni.model_executor.models.output_templates import OmniOutput
@@ -1094,9 +1095,8 @@ class Qwen3TTSTalkerForConditionalGeneration(nn.Module):
         # Resample to 24kHz for speaker encoder.
         target_sr = int(getattr(self.config.speaker_encoder_config, "sample_rate", 24000))
         if sr != target_sr:
-            from vllm.multimodal.audio import resample_audio_resampy
-
-            wav = resample_audio_resampy(wav.astype(np.float32), orig_sr=int(sr), target_sr=target_sr)
+            resampler = AudioResampler(target_sr=target_sr)
+            wav = resampler.resample(wav.astype(np.float32), orig_sr=int(sr))
             sr = target_sr
 
         # Follow official implementation: mel_spectrogram expects 24kHz.

vllm_omni/model_executor/models/qwen3_tts/qwen3_tts_tokenizer.py

@@ -22,7 +22,7 @@ import soundfile as sf
 import torch
 from torch.nn.utils.rnn import pad_sequence
 from transformers import AutoConfig, AutoFeatureExtractor, AutoModel
-from vllm.multimodal.audio import resample_audio_resampy
+from vllm.multimodal.audio import AudioResampler
 from vllm.multimodal.media.audio import load_audio as _load_audio_file
 
 from .tokenizer_12hz.configuration_qwen3_tts_tokenizer_v2 import Qwen3TTSTokenizerV2Config
@@ -161,7 +161,8 @@ class Qwen3TTSTokenizer:
             audio = np.mean(audio, axis=-1)
 
         if sr != target_sr:
-            audio = resample_audio_resampy(audio, orig_sr=sr, target_sr=target_sr)
+            resampler = AudioResampler(target_sr=target_sr)
+            audio = resampler.resample(audio, orig_sr=sr)
 
         return audio.astype(np.float32)
 
@@ -209,7 +210,8 @@ class Qwen3TTSTokenizer:
             if a.ndim > 1:
                 a = np.mean(a, axis=-1)
             if int(sr) != target_sr:
-                a = resample_audio_resampy(a.astype(np.float32), orig_sr=int(sr), target_sr=target_sr)
+                resampler = AudioResampler(target_sr=target_sr)
+                a = resampler.resample(a.astype(np.float32), orig_sr=int(sr))
             out.append(a.astype(np.float32))
         return out