k2-fsa/sherpa

Issues

• outputs of decode with contexts phrases are defferent between the jit-converted model and the original model

  #717 opened a month ago by RyuseiMigita
  3

• 方言

  #718 opened a month ago by zhouyi614
  1

• Whisper在Nvidia T4上模型转换失败

  #709 opened 2 months ago by harryfyodor
  2

• sherpa triton VS sherpa-onnx

  #716 opened a month ago by pehonnet
  2

• whisper 支持in-flight batch 了吗

  #710 opened 2 months ago by wangjxxxhi12
  5

• sherpa install document has a 404 link

  #712 opened a month ago by roronoa-zoro-d
  1

• zipformer transducer is going to slow when run multi threading

  #704 opened 2 months ago by dohe0342
  5

• Kokoro tts en

  #702 opened 2 months ago by SoulBreacher
  2

• Whisper triton server inference on jetson is failing with : Assertion failed: Encoder tokens are not given

  #688 opened 3 months ago by sasatte
  4

• whisper TensorRT-LLM 是不是还不支持语种识别能力

  #687 opened 3 months ago by Banner-Wang
  2

• Few domain related terminologies are not transcribed correctly in whisper-triton.

  #649 opened 6 months ago by krishnardt
  6

• Streaming zipformer tensorrt support

  #681 opened 4 months ago by francois-vz
  2

• Excessive Input Values in streaming zipformer encoder After Conversion to onnx

  #679 opened 4 months ago by renadnasser1
  4

• Is there any support Speaker diarisation

  #682 opened 4 months ago by sh1man
  6

• Long audios

  #678 opened 4 months ago by RuslanSel
  1

• nvcr.io/nvidia/tritonserver:24.10-trtllm-python-py3 build_qwen.sh 时报错 'PretrainedConfig' object has no attribute 'n_audio_ctx'

  #675 opened 4 months ago by zhuimin
  0

• wav2vec 解码问题

  #667 opened 4 months ago by winlaic
  0

• 24.09-trtllm-python-py3 使用 tensorrt-llm==0.15.0.dev2024101500 编译模型报错“undefined symbol: _ZN3c106detail14torchCheckFailEPKcS2_jRKSs”

  #674 opened 4 months ago by xqun3
  3

• whisper 并发推理问题

  #650 opened 6 months ago by xqun3
  3

• KeywordSpotter 能否单独暴露到 C API 中

  #673 opened 4 months ago by endink
  8

• Whisper without translation

  #652 opened 6 months ago by Plemeur
  3

• offline-nemo-enc-dec-ctc-model.cc:Init:98 'normalize_type' does not exist in the metadata

  #670 opened 5 months ago by dev-shvetsov
  3

• 您好，我按照triton/whisper中的readme文件（trt-llm：0.14.0.dev2024091700）执行，发现报错：Tensor:x is not an input tensor

  #651 opened 6 months ago by tianchengcheng-cn
  3

• Has offline zipformer TensorRT been supported?

  #637 opened 7 months ago by Vergissmeinicht
  14

• Help in compiling Sherpa as a standalone static executable

  #645 opened 7 months ago by danielizham
  6

• How to support language auto-detection instead of given a specific language

  #640 opened 7 months ago by evanxqs
  2

• TTS reading rhythm improvement

  #635 opened 7 months ago by zsogitbe
  0

• 您好，我请问一下建立了build之后里面没有bin文件夹

  #633 opened 8 months ago by aaaaamilk
  1

• Regarding sherpa's Benchmark for Conformer TRT encoder vs ONNX: Device Issues

  #624 opened 8 months ago by NLP-yzy
  3

• Looking for complete conversion from pretrained huggingface model

  #611 opened 9 months ago by lionsheep24
  7

• Can i use sherpa onnx directly on python ?

  #618 opened 9 months ago by Yessine1e
  1

• Who is available for Sherpa-related consulting

  #617 opened 9 months ago by danpovey
  0

• What about int8 weighs?

  #608 opened 10 months ago by AntonThai2022
  3

• How to add hot words in whisper prompt

  #597 opened 10 months ago by taorui-plus
  1

• Transcribe failed frequently after set batch size to 4

  #606 opened 10 months ago by evanxqs
  7

• trtllm-build --checkpoint_dir ${checkpoint_dir}/decoder failed

  #605 opened 10 months ago by evanxqs
  1

• Is there VAD in Triton whisper?

  #601 opened 10 months ago by evanxqs
  4

• How to add prompt for whisper in triton?

  #602 opened 10 months ago by evanxqs
  0

• There's no build.py in latest triton whisper example folder

  #600 opened 10 months ago by evanxqs
  2

• Why can't I execute this compile command-------- cmake --build . --config Release –- -m:6

  #594 opened 10 months ago by GrantLau1226
  2

• sharpa/triton/whisper下面的readme文件里的操作能不能合并到docker file中？

  #592 opened 10 months ago by taorui-plus
  1

• Whisper model cannot build with tensorrt llm

  #584 opened a year ago by billlyzhaoyh
  2

• Error while clicking Generate on IOS-SwiftUI TTS

  #585 opened a year ago by hafsalm
  0

• where is TTS triton codebase

  #581 opened a year ago by StephennFernandes
  3

• unable to launch Triton server on finetuned whisper model

  #568 opened a year ago by StephennFernandes
  6

• K2-fsa/sherpa/triton/whisper 目录下 bash launch_server.sh 启动后，curl访问返回值{"error":"Not Found"}

  #570 opened a year ago by taorui-plus
  2

• Any plan to support the --blank-penalty option in sherpa?

  #564 opened a year ago by qichilu
  1

• Any plan for use multi-thread WASM in sherpa-onnx as nodejs library, I need to use realtime recognition on Raspberry Pi 4B

  #563 opened a year ago by jackwei86
  0

• High Word Error Rates % in Large Whisper V3

  #552 opened a year ago by zhao-lun
  1

• k2fsa-zipformer-chinese-english-mixed 模型需要更新

  #545 opened a year ago by megazone87
  2