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
atsr
语帆de21c10a2e8a
diff --git a/funasr/models/lcbnet/model.py b/funasr/models/lcbnet/model.pyindex e83f8d783..15e2fa1c4 100644--- a/funasr/models/lcbnet/model.py+++ b/funasr/models/lcbnet/model.py@@ -426,12 +426,11 @@ class LCBNet(nn.Module):tokenizer=tokenizer)time2 = time.perf_counter()meta_data["load_data"] = f"{time2 - time1:0.3f}"- pdb.set_trace()audio_sample_list = sample_list[0]if len(sample_list) >1:ocr_sample_list = sample_list[1]else:- ocr_sample_list = [294, 0]+ ocr_sample_list = [[294, 0]]speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),frontend=frontend)time3 = time.perf_counter()