Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / linto-ai/whisper-timestamped issues and pull requests
#65 - Merge
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#65 - Merge
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#64 - Inconsistent number of segments error
Issue -
State: closed - Opened by olevanss over 1 year ago
- 27 comments
#64 - Inconsistent number of segments error
Issue -
State: closed - Opened by olevanss over 1 year ago
- 27 comments
#63 - Weird repetition on transcript
Issue -
State: closed - Opened by catalwaysright over 1 year ago
- 2 comments
#63 - Weird repetition on transcript
Issue -
State: closed - Opened by catalwaysright over 1 year ago
- 2 comments
#62 - [Bug] remove_last_null_duration_words
Issue -
State: closed - Opened by mmichelli over 1 year ago
- 7 comments
#62 - [Bug] remove_last_null_duration_words
Issue -
State: closed - Opened by mmichelli over 1 year ago
- 7 comments
#61 - AssertionError "assert len(segment_tokens_check) < len(segment["tokens"])" with option --accurate
Issue -
State: closed - Opened by agorman over 1 year ago
- 3 comments
#61 - AssertionError "assert len(segment_tokens_check) < len(segment["tokens"])" with option --accurate
Issue -
State: closed - Opened by agorman over 1 year ago
- 3 comments
#60 - Option --vad not working offline (when VAD torch model has been loaded already)
Issue -
State: closed - Opened by misutoneko over 1 year ago
- 1 comment
#60 - Option --vad not working offline (when VAD torch model has been loaded already)
Issue -
State: closed - Opened by misutoneko over 1 year ago
- 1 comment
#59 - Inconsistent number of segments: whisper_segments (1352) != timestamped_word_segments (1350)
Issue -
State: closed - Opened by jeremymatt over 1 year ago
- 5 comments
#59 - Inconsistent number of segments: whisper_segments (1352) != timestamped_word_segments (1350)
Issue -
State: closed - Opened by jeremymatt over 1 year ago
- 5 comments
#57 - AssertionError: Got empty transcription!
Issue -
State: closed - Opened by agorman over 1 year ago
- 4 comments
#57 - AssertionError: Got empty transcription!
Issue -
State: closed - Opened by agorman over 1 year ago
- 4 comments
#56 - [Bug] Unable to use multiple output formats directly (without "all")
Issue -
State: closed - Opened by misutoneko over 1 year ago
- 2 comments
#56 - [Bug] Unable to use multiple output formats directly (without "all")
Issue -
State: closed - Opened by misutoneko over 1 year ago
- 2 comments
#55 - Warning of onnxruntime "Removing initializer 'XXX'. It is not used by any node and should be removed from the model." with option --vad
Issue -
State: closed - Opened by Jeronymous over 1 year ago
#55 - Warning of onnxruntime "Removing initializer 'XXX'. It is not used by any node and should be removed from the model." with option --vad
Issue -
State: closed - Opened by Jeronymous over 1 year ago
#54 - Run Silero VAD before transcribing with Whisper (to reduce hallucinations)
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#54 - Run Silero VAD before transcribing with Whisper (to reduce hallucinations)
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#53 - Compatibility issues with openai-whisper version 20230306
Issue -
State: closed - Opened by Jeronymous over 1 year ago
- 1 comment
Labels: bug
#53 - Compatibility issues with openai-whisper version 20230306
Issue -
State: closed - Opened by Jeronymous over 1 year ago
- 1 comment
Labels: bug
#51 - Update to Whisper version 20230306
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#51 - Update to Whisper version 20230306
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#48 - Make Whisper Requirement more flexible to be able to use a specific Whisper version (as some breakages were introducted in 20230306)
Issue -
State: closed - Opened by kamranjon over 1 year ago
- 7 comments
#48 - Make Whisper Requirement more flexible to be able to use a specific Whisper version (as some breakages were introducted in 20230306)
Issue -
State: closed - Opened by kamranjon over 1 year ago
- 7 comments
#47 - Fatal Error: Got inconsistent text for segment 10
Issue -
State: closed - Opened by maptz over 1 year ago
- 5 comments
#47 - Fatal Error: Got inconsistent text for segment 10
Issue -
State: closed - Opened by maptz over 1 year ago
- 5 comments
#46 - Spot (probable) disfluencies in transcription
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#46 - Spot (probable) disfluencies in transcription
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#42 - How to write SRT file? Are models the same as whisper?
Issue -
State: closed - Opened by Adsc58 over 1 year ago
- 4 comments
Labels: question
#42 - How to write SRT file? Are models the same as whisper?
Issue -
State: closed - Opened by Adsc58 over 1 year ago
- 4 comments
Labels: question
#41 - Do not rely on whisper timestamps
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#41 - Do not rely on whisper timestamps
Pull Request -
State: closed - Opened by Jeronymous over 1 year ago
#40 - Consider Supporting CTranslate2 for faster inference
Issue -
State: open - Opened by kamranjon over 1 year ago
- 15 comments
Labels: enhancement
#40 - Consider Supporting CTranslate2 for faster inference
Issue -
State: open - Opened by kamranjon over 1 year ago
- 15 comments
Labels: enhancement
#39 - Question: How to efficiently get attention weights with beam search decoding?
Issue -
State: closed - Opened by ItakeLs over 1 year ago
- 3 comments
#39 - Question: How to efficiently get attention weights with beam search decoding?
Issue -
State: closed - Opened by ItakeLs over 1 year ago
- 3 comments
#38 - Different results with whisper and whisper_timestamped
Issue -
State: closed - Opened by skanda1005 over 1 year ago
- 9 comments
Labels: question
#38 - Different results with whisper and whisper_timestamped
Issue -
State: closed - Opened by skanda1005 over 1 year ago
- 9 comments
Labels: question
#37 - Suggestion: Problem with small words in SRT files
Issue -
State: closed - Opened by xaxole98 over 1 year ago
- 3 comments
Labels: question
#37 - Suggestion: Problem with small words in SRT files
Issue -
State: closed - Opened by xaxole98 over 1 year ago
- 3 comments
Labels: question
#36 - Suggestion: Use VAD to improve over Whisper's segment timestamps estimation
Issue -
State: closed - Opened by Jeronymous over 1 year ago
- 6 comments
Labels: enhancement
#36 - Suggestion: Use VAD to improve over Whisper's segment timestamps estimation
Issue -
State: closed - Opened by Jeronymous over 1 year ago
- 6 comments
Labels: enhancement
#35 - Suggestion: Add Speaker Diarization
Issue -
State: open - Opened by ubanning over 1 year ago
- 3 comments
Labels: enhancement
#35 - Suggestion: Add Speaker Diarization
Issue -
State: open - Opened by ubanning over 1 year ago
- 3 comments
Labels: enhancement
#34 - Word level output is combined for Languages that don't use spaces
Issue -
State: closed - Opened by kamranjon over 1 year ago
- 1 comment
#34 - Word level output is combined for Languages that don't use spaces
Issue -
State: closed - Opened by kamranjon over 1 year ago
- 1 comment
#33 - Whisper_timestamped does not transcript all the video?
Issue -
State: closed - Opened by aliscie over 1 year ago
- 8 comments
#33 - Whisper_timestamped does not transcript all the video?
Issue -
State: closed - Opened by aliscie over 1 year ago
- 8 comments
#32 - why whisper_timestamped does not transcript the entire video?
Issue -
State: closed - Opened by aliscie over 1 year ago
#32 - why whisper_timestamped does not transcript the entire video?
Issue -
State: closed - Opened by aliscie over 1 year ago
#31 - Add a max_line_length parameter to subtitle files
Issue -
State: closed - Opened by ubanning over 1 year ago
- 11 comments
#31 - Add a max_line_length parameter to subtitle files
Issue -
State: closed - Opened by ubanning over 1 year ago
- 11 comments
#30 - Word Timing Accuracy Falls Off After Pauses Example
Issue -
State: closed - Opened by kamranjon almost 2 years ago
- 4 comments
#30 - Word Timing Accuracy Falls Off After Pauses Example
Issue -
State: closed - Opened by kamranjon almost 2 years ago
- 4 comments
#29 - Specific functions don't work.
Issue -
State: closed - Opened by xaxole98 almost 2 years ago
- 3 comments
#29 - Specific functions don't work.
Issue -
State: closed - Opened by xaxole98 almost 2 years ago
- 3 comments
#28 - Issue of duplicate word lines
Issue -
State: closed - Opened by MohammedMehdiTBER almost 2 years ago
- 4 comments
#28 - Issue of duplicate word lines
Issue -
State: closed - Opened by MohammedMehdiTBER almost 2 years ago
- 4 comments
#27 - Delay in the word level transcription
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 3 comments
#27 - Delay in the word level transcription
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 3 comments
#26 - Sometimes segments with "no_speech_prob" larger than "speech threshold" and "avg_logprob" lower than "logprob_threshold" still appear
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 2 comments
#26 - Sometimes segments with "no_speech_prob" larger than "speech threshold" and "avg_logprob" lower than "logprob_threshold" still appear
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 2 comments
#25 - Verbose option does not support None (no output)
Issue -
State: closed - Opened by kamranjon almost 2 years ago
- 1 comment
#25 - Verbose option does not support None (no output)
Issue -
State: closed - Opened by kamranjon almost 2 years ago
- 1 comment
#24 - Inconsistent number of segments: whisper_segments (462) != timestamped_word_segments (461)
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 12 comments
#24 - Inconsistent number of segments: whisper_segments (462) != timestamped_word_segments (461)
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 12 comments
#23 - huggingface_hub.utils._validators.HFValidationError
Issue -
State: closed - Opened by boxabirds almost 2 years ago
- 7 comments
#23 - huggingface_hub.utils._validators.HFValidationError
Issue -
State: closed - Opened by boxabirds almost 2 years ago
- 7 comments
#22 - Clarifying whisperX limitations
Issue -
State: closed - Opened by m-bain almost 2 years ago
- 6 comments
Labels: documentation
#22 - Clarifying whisperX limitations
Issue -
State: closed - Opened by m-bain almost 2 years ago
- 6 comments
Labels: documentation
#21 - Fail with "***.en" models
Issue -
State: closed - Opened by alexgain almost 2 years ago
- 6 comments
#20 - Change licence
Pull Request -
State: closed - Opened by damienlaine almost 2 years ago
#19 - Possible failure "AssertionError: Fatal Error: Got inconsistent logprob for segment <...>: <...> != <...>"
Issue -
State: closed - Opened by Jeronymous almost 2 years ago
#18 - Suggestion: Print timestamped words on-the-fly with option verbose=True
Issue -
State: open - Opened by vedran almost 2 years ago
- 3 comments
Labels: enhancement
#17 - transcribe fails with error: `Argument #4: Padding size should be less than the corresponding input dimension, but got: padding (200, 200) at dimension 2 of input [1, 1, 144]`
Issue -
State: closed - Opened by eschmidbauer almost 2 years ago
- 6 comments
#16 - Transcription contains duplicated fragments
Issue -
State: closed - Opened by romanzoniit almost 2 years ago
- 5 comments
#15 - Got infinite logprob
Issue -
State: closed - Opened by tkorchagin almost 2 years ago
- 9 comments
#14 - "TypeError: can't convert cuda:0 device type tensor to numpy" with option --plot / plot_word_alignment on CUDA
Issue -
State: closed - Opened by WentingMiao almost 2 years ago
- 8 comments
#13 - AssertionError: Got inconsistent logprob at index <N>: <XXX> != <YYY>
Issue -
State: closed - Opened by Jeronymous almost 2 years ago
#12 - AssertionError: Got inconsistent logprobs length : 23 != 22
Issue -
State: closed - Opened by MohammedMehdiTBER almost 2 years ago
- 17 comments
#11 - How can align sentences instead of words?
Issue -
State: closed - Opened by MohammedMehdiTBER almost 2 years ago
- 1 comment
#10 - Suggestion: Support beam search / nbest decoding (temperature fallback...)
Issue -
State: closed - Opened by Jeronymous almost 2 years ago
#9 - "Got infinite logprob" assertion failure, with option condition_on_previous_text=False
Issue -
State: closed - Opened by ItakeLs almost 2 years ago
- 2 comments
#8 - Preparing metadata (setup.py)
Issue -
State: closed - Opened by romanzoniit almost 2 years ago
- 1 comment
#7 - Cannot run multiple transcriptions without reloading the model
Issue -
State: closed - Opened by KMC07 almost 2 years ago
- 1 comment
#6 - start + end outside length of audio
Issue -
State: open - Opened by doublex almost 2 years ago
- 9 comments
Labels: bug
#5 - CSV output changed to better match Gentle output
Pull Request -
State: closed - Opened by seanth almost 2 years ago
- 4 comments
#4 - AssertionError: Inconsistent number of segments: whisper_segments (12) != timestamped_word_segments (11)
Issue -
State: closed - Opened by romanzoniit almost 2 years ago
- 16 comments
#3 - word.strip()
Issue -
State: closed - Opened by doublex almost 2 years ago
- 3 comments
#2 - Update requirements.txt
Pull Request -
State: closed - Opened by seanth almost 2 years ago
#1 - WARNING:whisper_timestamped:Inconsistent number of segments:
Issue -
State: closed - Opened by tkorchagin almost 2 years ago
- 8 comments