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
test
语帆a88b51c5442e
diff --git a/examples/industrial_data_pretraining/lcbnet/demo2.sh b/examples/industrial_data_pretraining/lcbnet/demo2.shindex 0d5a4f031..9ba176be6 100755--- a/examples/industrial_data_pretraining/lcbnet/demo2.sh+++ b/examples/industrial_data_pretraining/lcbnet/demo2.sh@@ -6,7 +6,7 @@ python -m funasr.bin.inference \--config-name="config.yaml" \++init_param=${file_dir}/model.pb \++tokenizer_conf.token_list=${file_dir}/tokens.txt \-++input=[${file_dir}/wav.scp,${file_dir}/ocr_text] \+++input=[${file_dir}/wav.scp,${file_dir}/ocr.txt] \+data_type='["kaldi_ark", "text"]' \++tokenizer_conf.bpemodel=${file_dir}/bpe.model \++output_dir="./outputs/debug" \diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.pyindex d5225dee8..ba7dcabaa 100644--- a/funasr/auto/auto_model.py+++ b/funasr/auto/auto_model.py@@ -39,13 +39,11 @@ def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):filelist = [".scp", ".txt", ".json", ".jsonl"]chars = string.ascii_letters + string.digits- pdb.set_trace()if isinstance(data_in, str) and data_in.startswith('http'): # urldata_in = download_from_url(data_in)if isinstance(data_in, str) and os.path.exists(data_in): # wav_path; filelist: wav.scp, file.jsonl;text.txt;_, file_extension = os.path.splitext(data_in)file_extension = file_extension.lower()- pdb.set_trace()if file_extension in filelist: #filelist: wav.scp, file.jsonl;text.txt;with open(data_in, encoding='utf-8') as fin:for line in fin: