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 empty asr result (#1765)
彭震东bd3b18016d57
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.pyindex 23d25c9be..e8ca00817 100644--- a/funasr/auto/auto_model.py+++ b/funasr/auto/auto_model.py@@ -42,8 +42,9 @@ def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):filelist = [".scp", ".txt", ".json", ".jsonl", ".text"]chars = string.ascii_letters + string.digits- if isinstance(data_in, str) and data_in.startswith("http://"): # url- data_in = download_from_url(data_in)+ if isinstance(data_in, str):+ if data_in.startswith("http://") or data_in.startswith("https://"): # url+ data_in = download_from_url(data_in)if isinstance(data_in, str) and os.path.exists(data_in@@ -284,7 +285,7 @@ class AutoModel:with torch.no_grad():res = model.inference(**batch, **kwargs)if isinstance(res, (list, tuple)):- results = res[0]+ results = res[0] if len(res) > 0 else [{"text": ""}]meta_data = res[1] if len(res) > 1 else {}time2 = time.perf_counter()