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 stage0
游雁5e100f124427
diff --git a/examples/deepspeed_conf/ds_stage0.json b/examples/deepspeed_conf/ds_stage0.jsonnew file mode 100644index 000000000..661a6a0cb--- /dev/null+++ b/examples/deepspeed_conf/ds_stage0.json@@ -0,0 +1,30 @@+{+ "train_micro_batch_size_per_gpu": 1,+ "gradient_accumulation_steps": 1,+ "steps_per_print": 100,+ "gradient_clipping": 5,+ "fp16": {+ "enabled": false,+ "auto_cast": false,+ "loss_scale": 0,+ "initial_scale_power": 16,+ "loss_scale_window": 1000,+ "hysteresis": 2,+ "consecutive_hysteresis": false,+ "min_loss_scale": 1+ },+ "bf16": {+ "enabled": true+ },+ "zero_force_ds_cpu_optimizer": false,+ "zero_optimization": {+ "stage": 0,+ "allgather_partitions": true,+ "allgather_bucket_size": 5e8,+ "overlap_comm": true,+ "reduce_scatter": true,+ "reduce_bucket_size": 5e8,+ "contiguous_gradients": true,+ "round_robin_gradients": true+ }+}