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3eee773814c3
diff --git a/funasr/datasets/openai_datasets/datasets.py b/funasr/datasets/openai_datasets/datasets.pyindex 3bc6aa011..9c74ef188 100644--- a/funasr/datasets/openai_datasets/datasets.py+++ b/funasr/datasets/openai_datasets/datasets.py@@ -216,7 +216,7 @@ class OpenAIDataset(torch.utils.data.Dataset):if b < 2:beg = 0logging.info(- f"Warning, b * t: {b * t} > {self.batch_size}, b: {b}, t: {t}, drop half data {idx}th, beg:{beg}"+ f"Warning, b * t: {b * t} > {self.batch_size_scale_ratio_max} * {self.batch_size}, b: {b}, t: {t}, drop half data {idx}th, beg:{beg}")samples = samples[beg : beg + b : 2]continue