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
ds
游雁bbd300a91184
diff --git a/funasr/bin/train_ds.py b/funasr/bin/train_ds.pyindex 03cb18479..a4ae11b68 100644--- a/funasr/bin/train_ds.py+++ b/funasr/bin/train_ds.py@@ -198,7 +198,9 @@ def main(**kwargs):trainer.train_loss_avg = 0.0if trainer.rank == 0:- average_checkpoints(trainer.output_dir, trainer.avg_nbest_model)+ average_checkpoints(+ trainer.output_dir, trainer.avg_nbest_model, use_deepspeed=trainer.use_deepspeed+ )trainer.close()diff --git a/funasr/train_utils/average_nbest_models.py b/funasr/train_utils/average_nbest_models.pyindex 8553baa98..20da13022 100644--- a/funasr/train_utils/average_nbest_models.py+++ b/funasr/train_utils/average_nbest_models.py@@ -16,7 +16,7 @@ from collections import OrderedDictfrom functools import cmp_to_key-def _get_checkpoint_paths(output_dir: str, last_n: int = 5, use_deepspeed=False):+def _get_checkpoint_paths(output_dir: str, last_n: int = 5, use_deepspeed=False, **kwargs):"""Get the paths of the last 'last_n' checkpoints by parsing filenamesin the output directory.@@ -55,7 +55,7 @@ def average_checkpoints(output_dir: str, last_n: int = 5, **kwargs):Average the last 'last_n' checkpoints' model state_dicts.If a tensor is of type torch.int, perform sum instead of average."""- checkpoint_paths = _get_checkpoint_paths(output_dir, last_n)+ checkpoint_paths = _get_checkpoint_paths(output_dir, last_n, **kwargs)print(f"average_checkpoints: {checkpoint_paths}")state_dicts = []