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 seaco paraformer
维石c0e5107b3924
diff --git a/runtime/python/libtorch/demo_seaco_paraformer.py b/runtime/python/libtorch/demo_seaco_paraformer.pynew file mode 100644index 000000000..d54dce537--- /dev/null+++ b/runtime/python/libtorch/demo_seaco_paraformer.py@@ -0,0 +1,13 @@+import torch+from pathlib import Path+from funasr_torch.paraformer_bin import SeacoParaformer++model_dir = "iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"+device_id = 0 if torch.cuda.is_available() else -1+model = SeacoParaformer(model_dir, batch_size=1, device_id=device_id) # gpu++wav_path = "{}/.cache/modelscope/hub/{}/example/asr_example.wav".format(Path.home(), model_dir)+hotwords = "你的热词 魔哒"++result = model(wav_path, hotwords)+print(result)