Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
fix bug
游雁1186cd96a5a8
diff --git a/funasr/datasets/audio_datasets/samplers.py b/funasr/datasets/audio_datasets/samplers.pyindex f8f744c55..f7057de11 100644--- a/funasr/datasets/audio_datasets/samplers.py+++ b/funasr/datasets/audio_datasets/samplers.py@@ -399,10 +399,7 @@ class CustomDistributedBufferDynamicBatchSampler(DistributedSampler):continuesample_length = 1 if self.batch_type == "example" else original_sample_lengthpotential_batch_length = max(max_len_in_batch, sample_length) * (len(batch) + 1)- if (- potential_batch_length <= self.batch_size- and count <= self.batch_size_sample_max- ):+ if potential_batch_length <= self.batch_size and count < self.batch_size_sample_max:batch.append(idx)max_len_in_batch = max(max_len_in_batch, sample_length)count += 1