huggingface / speechbox

huggingface/speechbox Issues

JSON serialization not available in pyannote.core 5.x
Updated 20 days ago7
ValueError: attempt to get argmin of an empty sequence
Updated a month ago12
TypeError: AutomaticSpeechRecognitionPipeline._sanitize_parameters() got an unexpected keyword argument 'use_auth_token'
Updated a month ago1
Language Selection is Not Available for Whisper Model
Updated a month ago
AttributeError: 'Annotation' object has no attribute 'for_json'
Closed a month ago6
OSError: automatic-speech-recognition is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
Closed a month ago2
got an unexpected keyword argument 'use_auth_token'
Updated 3 months ago5
Error with speaker diarization and transcription
Updated 6 months ago2
TypeError: unsupported operand type(s) for -: 'NoneType' and 'float'
Updated 6 months ago3
Add support for specifying the number of speakers in ASRDiarizationPipeline
Updated 10 months ago5
TypeError: AutomaticSpeechRecognitionPipeline._sanitize_parameters() got an unexpected keyword argument 'use_auth_token'
Closed 10 months ago5
Puctuation restoration from trascript and wav file
Updated 10 months ago1
Inverse text normalization of numbers etc.
Updated a year ago1
Unwanted automatic translation of non-english input to diarization.
Closed a year ago2
Error with: ASR With Speaker Diarization Example
Closed a year ago5
ASP Diarization Performance
Updated a year ago3
ASRDiarizationPipeline processing time
Updated a year ago2
Loading a custom audio sample into the diarization pipeline
Closed a year ago2
'GenerationConfig' object has no attribute 'no_timestamps_token_id'
Closed a year ago8
An idea for enhancing punctuation restoration for non-space separated languages
Updated a year ago1
Anyone have demo source code to process file with whisper large model and get outputs as vtt srt?
Updated a year ago2
what speech processing will be included?
Updated a year ago1
[New Task] Add timestamp alignment
Updated a year ago5
Restore punctuation for audios no 16k
Closed a year ago2
Text-only approach to punctuation restoration Pro/Con
Updated a year ago1