FunASR
FunASR copied to clipboard
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Notice: In order to resolve issues more efficiently, please raise issue following the template. (注意:为了更加高效率解决您遇到的问题,请按照模板提问,补充细节) ## ❓ Questions and Help 请问funasr里面流式Paraformer,在SANMEncoderChunkOpt里面的chunk默认为 [12, 15] 分别代表什么,左看12,chunksize 15吗;我看推理的代码chunksize传入的长度为3(比如 [0, 10, 5] ### Before...
Hello, I want to pretrain the Paraformer-large instead of fine-tuning. Since the **language is different**, I need to **reconstruct the tokenzier** and can not use the fine-tune.sh script. Based on...
#### paraformer-large-vocab8404,给定seg_dict中英文为bpe序列,对于不在seg_dict中的英文单词如何生成子词序列,有没有bpe.model? #### seg_dict部分: ``` . . @ @ aaaaa a@@ a@@ a@@ a@@ a aaanthor a@@ a@@ an@@ th@@ or aabar a@@ ab@@ ar aace a@@ ace aachen a@@...
## 实时语音识别示例代码报错 ### Before asking: 1. search the issues. 2. search the docs. #### Code ```python from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess model_dir = "iic/SenseVoiceSmall" chunk_size = [0,...
Notice: In order to resolve issues more efficiently, please raise issue following the template. (注意:为了更加高效率解决您遇到的问题,请按照模板提问,补充细节) ## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the...
C++编译asr离线gpu模式,编译运行可以成功运行,但是发现没办法指定gpu卡运行。看了代码传的参数 TCLAP::SwitchArg use_gpu("", INFER_GPU, "Whether to use GPU, default is false", false); 只支持true或者fasle.继续看代码,发现初始模型时候 asr_handle = FunOfflineInit(model_path, thread_num, use_gpu, batch_size); 这个方法FunOfflineInit没办法继续下一步查看。 现在想要指定卡运行,希望得到支持
Notice: In order to resolve issues more efficiently, please raise issue following the template. (注意:为了更加高效率解决您遇到的问题,请按照模板提问,补充细节) ## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the...
部署的cpu镜像: sudo docker run -p 10097:10095 -it --privileged=true \ -v $PWD/funasr-runtime-resources/models:/workspace/models \ --name funasr_test \ registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12 配置如下: nohup bash run_server_2pass.sh \ --download-model-dir /workspace/models \ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \ --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx \...
2025-02-14 06:53:51,413 - DEBUG - subprocess.call(['ffmpeg', '-y', '-read_ahead_limit', '-1', '-i', 'cache:pipe:0', '-vn', '-f', 'wav', '-']) 2025-02-14 06:53:51,424 - DEBUG - subprocess.call(['ffmpeg', '-y', '-read_ahead_limit', '-1', '-i', 'cache:pipe:0', '-vn', '-f', 'wav', '-'])...