SYSTRAN/faster-whisper

Issues

• [Feature Request] Constrain Available Languages when Autodetecting Language

  #1164 opened a month ago by WesleyFister
  4

• download_model warning

  #1196 opened 16 days ago by benbro
  1

• API call

  #1197 opened 13 days ago by denisjoshua
  6

• Version 1.1.0 has onnxruntime thread affinity crash

  #1169 opened 14 days ago by Appfinity-development
  9

• OOM when using VAD

  #1193 opened 14 days ago by Troffifi
  2

• Lack of GPU Parallelism for Real-Time Server Using Faster-Whisper

  #1192 opened 20 days ago by dariopellegrino00
  4

• BatchedInferencePipeline degrades transcription quality heavily

  #1179 opened a month ago by Appfinity-development
  11

• libcudnn_cnn problem

  #1182 opened 25 days ago by 781574155
  2

• sound-effects missing on output for beam-size > 1

  #1170 opened 19 days ago by rummyr
  3

• transcribe output number

  #1190 opened 20 days ago by ZhikangNiu
  0

• Batched inference on multiple audios

  #1177 opened a month ago by Deep-unlearning
  4

• lib `audio.py` error when transcribing `.webm` file

  #1185 opened 23 days ago by huzaifahj
  1

• batched inference generating inaccurate segments

  #1175 opened a month ago by Saccarab
  10

• Greater error when converted via ctranslate2

  #1168 opened a month ago by hforghani
  12

• Number sequence is not transcribed when a chunk starts with it

  #1174 opened a month ago by vkras
  1

• Poor performance for Vietnamese diarization

  #1176 opened a month ago by dohuyduc2002
  0

• no_speech_prob always returns 0.0.

  #1128 opened a month ago by giaoyyds
  1

• No need to install cuda driver?

  #1147 opened a month ago by ILG2021
  1

• comparison of Turbo Models

  #1149 opened a month ago by xipingL
  10

• WER on benchmark tables

  #1172 opened a month ago by asr-lord
  3

• Add the possibility of using `return_logits_vocab` from Ctranslate2

  #1151 opened a month ago by pierrepv8
  1

• Long audio needs much more time to transcribe

  #1156 opened a month ago by terryops
  1

• v1.1.0 slower than v1.0.3 on CPU

  #1167 opened a month ago by pablopla
  0

• how not to get the Smooth text

  #1165 opened a month ago by LRY1994
  0

• New model: CrisperWhisper

  #1162 opened a month ago by imsakg
  1

• Time for a new release?

  #1155 opened a month ago by RuntimeRacer
  2

• IndexError: list index out of range in add_word_timestamps function

  #1118 opened a month ago by formater
  10

• Batch size impact on speed and VRAM consumption

  #1143 opened a month ago by vidalfer
  4

• how can i not to get the normalized chinese number?

  #1152 opened a month ago by LRY1994
  1

• Can I serve speechbrain trained model whisper with faster whisper?

  #1139 opened a month ago by cod3r0k
  5

• Whisper Turbo model run on a CPU

  #1144 opened a month ago by joseph16388
  3

• cannot import name 'BatchedInferencePipeline'

  #1123 opened a month ago by acclayer7
  1

• nce

  #1145 opened a month ago by pierrepv8
  1

• Some segment has a 1 second shifted after PR #856

  #1140 opened a month ago by heimoshuiyu
  0

• Transcription error related to BatchedInferencePipeline and numpy

  #1102 opened a month ago by shkstar
  3

• Hidden state / embeddings of encoder

  #1132 opened a month ago by SinanAkkoyun
  2

• VAD Filter causing ValueError with silent audio segments during streaming

  #1127 opened a month ago by FrankyKyaw
  2

• Is this compatible with tinydiarize?

  #1116 opened a month ago by mathigatti
  1

• Some questions about outputting uppercase letters

  #1130 opened a month ago by zhuangzhuangliu2345
  0

• fasterwhisper and cuda version

  #1120 opened a month ago by zhuangzhuangliu2345
  7

• Issue with segments when the model doesn't output end time for segment.

  #1100 opened 2 months ago by bchinnari
  17

• Use multiple GPUs to process queue

  #1126 opened a month ago by theodufort
  1

• After using VAD, the start and end times of the recognized segments are incorrect

  #1119 opened 2 months ago by zlyMaster
  3

• min_silence_duration_ms is not working, Silence detection not working

  #1108 opened 2 months ago by andriken
  5

• Possible way to integrate support for Intel Iris Xe gpus?

  #1121 opened 2 months ago by gimmeAll
  1

• distill model ignores language

  #1122 opened 2 months ago by trigsoft
  1

• Custom VAD config with BatchedInferencePipeline

  #1109 opened 2 months ago by vidalfer
  1

• RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version

  #1115 opened 2 months ago by SwAt1563
  2

• Illegal instruction docker container

  #1117 opened 2 months ago by danpuz
  0

• no

  #1110 opened 2 months ago by majisama
  0