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de11189e9634
diff --git a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.py b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.pyindex e5e3e2302..41b344028 100644--- a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.py+++ b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.py@@ -28,6 +28,9 @@ model = AutoModel(init_param=f"{os.path.join(ckpt_dir, ckpt_id)}",output_dir=output_dir,device=device,+ fp16=False,+ bf16=False,+ llm_dtype="bf16",)diff --git a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.shindex 8e22cb955..bb63d4490 100644--- a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh+++ b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh@@ -41,7 +41,7 @@ for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text}&done-+wait#for data_set in "s2tt_en2zh.v20240605.test.jsonl"; do# jsonl=${jsonl_dir}/${data_set}# output_dir=${out_dir}/${data_set}