Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / xinjli/allosaurus issues and pull requests

#80 - preprocess.py literal comparison using equals

Pull Request - State: open - Opened by peterroelants 10 months ago

#76 - Fix setup.py

Issue - State: open - Opened by Fhrozen over 1 year ago

#75 - AttributeError: 'PosixPath' object has no attribute 'startswith'

Issue - State: closed - Opened by ThomasBallatore over 1 year ago - 1 comment

#74 - Content of fine-tuning files?

Issue - State: open - Opened by MarsMV almost 2 years ago

#72 - Any way to add new languages?

Issue - State: open - Opened by michaelpginn about 2 years ago

#71 - Rename all "model" variables and modules with full names

Pull Request - State: closed - Opened by emersonknapp over 2 years ago - 1 comment

#70 - Wave error for given sample

Issue - State: open - Opened by sonal-ssj over 2 years ago

#69 - Difference in outputs of splitted v/s unsplitted audio file

Issue - State: closed - Opened by 007prateekd over 2 years ago - 2 comments

#68 - make the output of "feature_window" function chronological

Pull Request - State: open - Opened by padster06 over 2 years ago

#67 - NumPy requirement is less than 1.22 and latest is 1.19.5

Issue - State: open - Opened by SteveC00k over 2 years ago

#66 - add emit_frame.py

Pull Request - State: open - Opened by cckk2913 over 2 years ago

#65 - Directory Name con not allowed on Windows

Issue - State: open - Opened by steveway over 2 years ago - 1 comment

#64 - Feature normalization can cause NaN to appear

Issue - State: open - Opened by rcontrai over 2 years ago - 1 comment

#63 - Unable to run interspeech21 model

Issue - State: open - Opened by SlistInc over 2 years ago - 1 comment

#62 - The timestamp of model 'interspeech21' is incorrect

Issue - State: open - Opened by owaski almost 3 years ago - 5 comments

#61 - more model for recognition

Issue - State: open - Opened by bongblender almost 3 years ago - 1 comment

#60 - Not able to transcribe simple word what in English

Issue - State: closed - Opened by FilBot3 almost 3 years ago - 5 comments

#59 - support for python 3.10

Issue - State: open - Opened by bongblender almost 3 years ago - 4 comments

#58 - Optimizing for Latency

Issue - State: open - Opened by mattare2 about 3 years ago

#57 - Prior.txt file path

Issue - State: closed - Opened by Celine-Guan about 3 years ago - 2 comments

#56 - The timestamp's duration always be 0.045

Issue - State: closed - Opened by z451538473 about 3 years ago - 2 comments

#55 - Is the output phone or phonemes?

Issue - State: closed - Opened by raotnameh about 3 years ago - 2 comments

#54 - maximum size for Inventory CustomizationIs?

Issue - State: open - Opened by ElafIslam123 about 3 years ago - 1 comment

#53 - Issue with using dependencies numpy with numba and panphon

Issue - State: closed - Opened by ytan101 about 3 years ago

#52 - using 'eval' insted of 'distance' in trainer.py

Issue - State: open - Opened by ElafIslam123 about 3 years ago - 1 comment

#51 - 请问没有中文语言的支持吗

Issue - State: open - Opened by lvZic about 3 years ago - 4 comments

#50 - recording best practice to get best result ?

Issue - State: open - Opened by allan-simon about 3 years ago - 9 comments

#49 - Any explanation on feature window re-ordering?

Issue - State: open - Opened by Jackbennett about 3 years ago - 2 comments

#48 - allosaurus results for Persian language

Issue - State: open - Opened by sajede over 3 years ago - 2 comments

#47 - pip download

Issue - State: open - Opened by jacbrixey over 3 years ago - 4 comments

#46 - add interspeech2021 compositional_phonetics model

Pull Request - State: open - Opened by xinjli over 3 years ago

#45 - Don't completely hide the download exception

Pull Request - State: closed - Opened by willstott101 over 3 years ago

#44 - Remove duplicated resample_audio function

Pull Request - State: closed - Opened by willstott101 over 3 years ago - 1 comment

#43 - Realtime? (low-latency streaming inference)

Issue - State: open - Opened by willstott101 over 3 years ago - 5 comments

#42 - tqdm required by prep_feat, prep_token

Pull Request - State: closed - Opened by zaidsheikh over 3 years ago - 1 comment

#41 - Bypass the filename check when it is an instance of BytesIO objects

Pull Request - State: closed - Opened by kormoczi over 3 years ago - 1 comment

#40 - How the different phonemes sounds exactly? (Preparation for fine-tuning...)

Issue - State: open - Opened by kormoczi over 3 years ago - 11 comments

#39 - Input wav file as a BytesIO object not working

Issue - State: closed - Opened by kormoczi over 3 years ago - 5 comments

#38 - Phone duration is always 0.045

Issue - State: open - Opened by artrayd over 3 years ago - 6 comments

#37 - Issue with shapes alignment

Issue - State: closed - Opened by anushakabber over 3 years ago - 6 comments

#36 - added the return_lstm and return_both options in the recognizer

Pull Request - State: closed - Opened by raotnameh over 3 years ago - 1 comment

#35 - Option to extract last layer embeddings of the lstm.

Issue - State: closed - Opened by raotnameh over 3 years ago - 3 comments

#34 - Loss for recognizing a part of audio

Issue - State: open - Opened by Enternal17 over 3 years ago - 2 comments

#33 - Cannot open 32 bit floating audio file

Issue - State: open - Opened by freddy5566 over 3 years ago - 4 comments

#32 - Phone distance metric

Issue - State: closed - Opened by mattare2 over 3 years ago - 3 comments

#31 - audio file size limit?

Issue - State: closed - Opened by somiljain7 over 3 years ago - 2 comments

#30 - Progress Information possible

Issue - State: open - Opened by steveway over 3 years ago - 3 comments

#29 - Can't download models

Issue - State: closed - Opened by JazminVidal over 3 years ago - 2 comments

#28 - Preliminary support to choose model location.

Pull Request - State: closed - Opened by steveway over 3 years ago - 1 comment

#27 - assert wave_path.exists()

Issue - State: closed - Opened by jesserme over 3 years ago - 5 comments

#26 - Support Speaker Diarization

Issue - State: closed - Opened by steveway over 3 years ago - 2 comments

#25 - Checking the full language list raised IndexError

Issue - State: open - Opened by yistLin over 3 years ago - 2 comments

#24 - Timestamps for phones?

Issue - State: closed - Opened by turian almost 4 years ago - 4 comments

#23 - system not deterministic

Issue - State: open - Opened by EricLefe almost 4 years ago - 1 comment

#22 - urllib.error.URLError: <urlopen error [Errno 60] Operation timed out>

Issue - State: closed - Opened by freddy5566 about 4 years ago - 5 comments

#21 - Deterministic output

Issue - State: closed - Opened by eremingt about 4 years ago - 2 comments

#20 - Phone times?

Issue - State: closed - Opened by eremingt about 4 years ago - 5 comments

#19 - How was the training data processed?

Issue - State: closed - Opened by Pita about 4 years ago - 7 comments

#18 - WASM support?

Issue - State: closed - Opened by Pita about 4 years ago - 1 comment

#17 - Runtime Error

Issue - State: closed - Opened by CHARLESYAN1 about 4 years ago - 1 comment

#16 - Segmentation fault

Issue - State: closed - Opened by unilight about 4 years ago - 3 comments

#15 - Update phones in a language

Issue - State: closed - Opened by babat00nday about 4 years ago - 1 comment

#14 - Support for custom phoneme symbols beyond IPA

Issue - State: open - Opened by babat00nday over 4 years ago

#13 - Change the location for the downloaded model

Issue - State: open - Opened by babat00nday over 4 years ago - 3 comments

#11 - Does allosaurus handle mixed speech and non-speech data?

Issue - State: closed - Opened by dinkar--s over 4 years ago - 5 comments

#10 - Build issue

Issue - State: closed - Opened by dinkar--s over 4 years ago - 2 comments

#9 - Phoneme Boundaries

Issue - State: closed - Opened by AASHISHAG over 4 years ago - 6 comments

#8 - Small bug fixes in trainer.py

Pull Request - State: closed - Opened by ajd12342 over 4 years ago - 1 comment

#7 - Fixed torch_load to load on GPU device_id rather than GPU 0

Pull Request - State: closed - Opened by ajd12342 over 4 years ago - 1 comment

#6 - Added ascii encoding(with ignore) for list_lang

Pull Request - State: closed - Opened by saikrishnarallabandi over 4 years ago

#5 - Unable to use the model

Issue - State: closed - Opened by AASHISHAG over 4 years ago - 2 comments

#4 - device-id argument doesn't work for different GPUs

Issue - State: closed - Opened by ajd12342 over 4 years ago - 1 comment

#3 - Incorrect command for downloading model

Issue - State: closed - Opened by ajd12342 over 4 years ago - 1 comment

#2 - Suggestions for README

Issue - State: closed - Opened by neubig over 4 years ago - 2 comments

#1 - Incomplete phone inventory for iso gup

Issue - State: open - Opened by complinger over 4 years ago - 3 comments