update

examples/conv_tasnet/run.sh

@@ -3,7 +3,7 @@
 : <<'END'
 
 
-sh run.sh --stage 2 --stop_stage 2 --system_version centos --file_folder_name file_dir --final_model_name conv-tasnet-dns3-20250319 \
+sh run.sh --stage 1 --stop_stage 2 --system_version centos --file_folder_name file_dir --final_model_name conv-tasnet-dns3-20250319 \
 --noise_dir "/data/tianxing/HuggingDatasets/nx_noise/data/noise/dns3-noise" \
 --speech_dir "/data/tianxing/HuggingDatasets/nx_noise/data/speech/dns3-speech" \
 --max_epochs 400

examples/conv_tasnet/step_1_prepare_data.py

@@ -136,7 +136,7 @@ def main():
                 "random1": random1,
             }
             row = json.dumps(row, ensure_ascii=False)
-            if random2 < (1 / 300 / 2):
+            if random2 < (1 / 300 / 1):
                 fvalid.write(f"{row}\n")
             else:
                 ftrain.write(f"{row}\n")

toolbox/torchaudio/metrics/pesq.py

@@ -47,7 +47,7 @@ def run_pesq_score(clean_audio_list: List[np.ndarray],
                    sample_rate: int = 16000,
                    mode: str = "wb",
                    n_jobs: int = 4,
-                   ) -> List[float]:
+                   ) -> float:
 
     pesq_score_list = run_batch_pesq(clean_audio_list=clean_audio_list,
                                      noisy_audio_list=noisy_audio_list,