Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

update

游雁d929c8e0f7bf
diff --git a/funasr/bin/compute_audio_cmvn.py b/funasr/bin/compute_audio_cmvn.py
index 6282e707c..cd64329c3 100644
--- a/funasr/bin/compute_audio_cmvn.py
+++ b/funasr/bin/compute_audio_cmvn.py
@@ -59,6 +59,7 @@ def main(**kwargs):
dataset_conf = kwargs.get("dataset_conf")
dataset_conf["batch_type"] = "example"
dataset_conf["batch_size"] = 1
+ dataset_conf["num_workers"] = os.cpu_count() or 32
batch_sampler_train = batch_sampler_class(dataset_train, is_training=False, **dataset_conf)
dataloader_train = torch.utils.data.DataLoader(dataset_train, collate_fn=dataset_train.collator, **batch_sampler_train)