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
decoding
游雁83d644c899b2
diff --git a/funasr/datasets/openai_datasets/index_ds.py b/funasr/datasets/openai_datasets/index_ds.pyindex cc518f807..9943e2a9c 100644--- a/funasr/datasets/openai_datasets/index_ds.py+++ b/funasr/datasets/openai_datasets/index_ds.py@@ -15,11 +15,6 @@ class OpenAIIndexDSJsonl(torch.utils.data.Dataset): # torch.utils.data.Datasetdef __init__(self, path: str, **kwargs):super().__init__()- self.max_source_length = kwargs.get("max_source_length", 2048)- self.min_source_length = kwargs.get("min_source_length", 0)- self.max_target_length = kwargs.get("max_target_length", 2048)- self.min_target_length = kwargs.get("min_target_length", 0)- self.max_token_length = kwargs.get("max_token_length", 2200)is_training = kwargs.get("is_training", True)if not (path.endswith(".jsonl") or path.endswith(".json")):diff --git a/funasr/train_utils/trainer_ds.py b/funasr/train_utils/trainer_ds.pyindex ba8dd1641..0fbac966f 100644--- a/funasr/train_utils/trainer_ds.py+++ b/funasr/train_utils/trainer_ds.py@@ -287,7 +287,9 @@ class Trainer:elif self.use_fsdp:passelif self.rank == 0:- logging.info(f"Save checkpoint: {epoch}, rank: {self.local_rank}\n")+ logging.info(+ f"Save checkpoint: {epoch}, rank: {self.rank}, local_rank: {self.local_rank}\n"+ )# self.step_or_epoch += 1state = {"epoch": epoch,