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
update
游雁47395c976f75
diff --git a/funasr/datasets/llm_datasets/datasets.py b/funasr/datasets/llm_datasets/datasets.pyindex ab0e48a45..9673d7662 100644--- a/funasr/datasets/llm_datasets/datasets.py+++ b/funasr/datasets/llm_datasets/datasets.py@@ -37,13 +37,13 @@ class AudioLLMDataset(torch.utils.data.Dataset):self.data_type = "sound"self.tokenizer = tokenizer- self.int_pad_value = int_pad_valueself.float_pad_value = float_pad_valueself.prompt = kwargs.get("prompt", "Transcribe speech to text.")self.prompt_pre = "USER: \nINSTRUCTION: {}\nINPUT: ".format(self.prompt) # "USER: \nINSTRUCTION: {}\nnINPUT: {}\nASSISTANT: "self.prompt_af = ""self.IGNORE_INDEX = kwargs.get("IGNORE_INDEX", -100)+ self.int_pad_value = self.IGNORE_INDEXdef get_source_len(self, index):item = self.index_ds[index]