1 Pull request merged by 1 person

• Added Phoneme-Based ASR Model for Tagalog

  #1067 merged Feb 23, 2025

1 Pull request opened by 1 person

• Add jr, sr, and ph.d to punkt abbreviations

  #1053 opened Feb 18, 2025

26 Issues closed by 1 person

• RuntimeError: Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model

  #689 closed Feb 19, 2025

• Model has been downloaded but the SHA256 checksum does not not match

  #389 closed Feb 19, 2025

• New English ASR model Distil-Whisper

  #550 closed Feb 19, 2025

• Support for stdin and and stdout

  #403 closed Feb 19, 2025

• simple split audio file example using whisperx

  #437 closed Feb 19, 2025

• Is it possible to use insanely-fast-whisper instead of faster-whisper?

  #614 closed Feb 19, 2025

• Distil-Whisper support?

  #558 closed Feb 19, 2025

• How do I create a huggingface space of the current version of whisperx?

  #631 closed Feb 19, 2025

• Where are the example/sample wav files?

  #325 closed Feb 19, 2025

• Always crashes at alignment stage

  #198 closed Feb 19, 2025

• Hallucination causes failure to align - uncleaned input in whisper dataset

  #230 closed Feb 19, 2025

• Linux install issues

  #242 closed Feb 19, 2025

• Add Arabic models

  #247 closed Feb 19, 2025

• Somewhat unclear instructions (Readme.md) regarding alignment model size

  #256 closed Feb 19, 2025

• Alignment Issue?

  #184 closed Feb 19, 2025

• huggingface error

  #261 closed Feb 19, 2025

• Sentence based timestamps

  #142 closed Feb 19, 2025

• out of sync for part of the file

  #151 closed Feb 19, 2025

• FileNotFoundError

  #925 closed Feb 19, 2025

• WhisperX can Generate the N-best (top few) hypotheses?

  #921 closed Feb 19, 2025

• Using Whisperx using Nvidia Triton

  #938 closed Feb 19, 2025

• Are there any Fork Projects currently in progress?

  #934 closed Feb 19, 2025

• Question about Min-Cut Operation and Silero Model Handling of Long Segments

  #1015 closed Feb 19, 2025

• Why perform speaker diarization at the end

  #1043 closed Feb 19, 2025

• whisperX vs fasterWhisper

  #1037 closed Feb 19, 2025

• Can't transcribe the mp3 or wav audio in the format given.

  #1052 closed Feb 19, 2025

3 Issues opened by 3 people

• Feature Request: Add token-based authentication support for downloading the base model in whisperx.load_model

  #1068 opened Feb 24, 2025

• Comparing WhisperX and Faster-Whisper on RunPod: Speed, Accuracy, and Optimization

  #1066 opened Feb 22, 2025

• Real Time Diarization for Streaming Audio Chunks in Custom ASR Pipeline

  #1065 opened Feb 21, 2025

12 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• make sure the leading and tailing word boundary exists.

  #1019 commented on Feb 21, 2025 • 4 new comments

• pip install whisperx results in installation of torch >2.0.0

  #1051 commented on Feb 18, 2025 • 0 new comments

• New warnings in v3.3.1 acceptable?

  #998 commented on Feb 19, 2025 • 0 new comments

• Feature Request: Whisper Tensorrt-llm backend support

  #624 commented on Feb 19, 2025 • 0 new comments

• tensors used as indices must be long, int, byte or bool tensors

  #1048 commented on Feb 19, 2025 • 0 new comments

• cpu utilisation maxes at 50% (conda?)

  #890 commented on Feb 20, 2025 • 0 new comments

• OOM with --diarize on long audio (4 hours)

  #951 commented on Feb 22, 2025 • 0 new comments

• Can't get cuda to work.

  #983 commented on Feb 22, 2025 • 0 new comments

• Diarization too slow

  #274 commented on Feb 22, 2025 • 0 new comments

• Could not load library libcudnn_ops_infer.so.8. on newest version.

  #967 commented on Feb 24, 2025 • 0 new comments

• Force Alignment with original text

  #1009 commented on Feb 24, 2025 • 0 new comments

• Speaker embeddings

  #952 commented on Feb 19, 2025 • 0 new comments