nyrahealth/CrisperWhisper
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
PythonNOASSERTION
Issues
- 0
torch.index_select() => IndexError: index 447 is out of bounds for dimension 2 with size 447
#20 opened by guynich - 1
How can I set ASR language?
#15 opened by hforghani - 8
Strange results for short audio clips
#1 opened by tjongsma - 1
Crisper Faster Whisper Turbo version?
#19 opened by aaa3334 - 0
Transcript problem using another language
#18 opened by Youssef-Barakat - 0
- 5
Takes too much VRAM to transcribe audios
#13 opened by PS-AI - 4
IndexError in Whisper model: Index out of bounds during token timestamp extraction
#12 opened by GrahLnn - 1
Enumerating-based Clinical Assessments
#14 opened by david-gimeno - 6
Gradio app on ZeroGPU Huggingface Spaces
#11 opened by yvrjsharma - 5
- 6
- 1
no dysfluencies
#10 opened by bisserai - 1
Retokenization
#8 opened by kelseyjd - 3
- 6
- 4
IndexError: list index out of range
#4 opened by TechInterMezzo - 1
Plan to release smaller models
#5 opened by HKAB - 1
Training with spanish datasets?
#2 opened by rmajasol