xinjli allosaurus issues

xinjli / allosaurus

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

GNU General Public License v3.0

571 stars 88 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

I want to use the phonemes from the languages in "latest" to create phoneme text files with Epitran.

#81 bukefenjie opened 4 days ago
0
preprocess.py literal comparison using equals

#80 peterroelants opened 7 months ago
0
How long does it theoretically take for "allosaurus" to recognize phonemes?

#79 Yihuan-qaq opened 1 year ago
0
Is there any way of getting arpabet phonetic transcription for hindi language?

#78 debasishaimonk opened 1 year ago
0
Phone inventory always the default one even after specifying model eng2102 and lang eng

#77 BeauGeogeo opened 1 year ago
0
Fix setup.py

#76 Fhrozen opened 1 year ago
0
AttributeError: 'PosixPath' object has no attribute 'startswith'

#75 ThomasBallatore closed 1 year ago
1
Content of fine-tuning files?

#74 MarsMV opened 1 year ago
0
UnicodeEncodeError: 'charmap' codec can't encode character '\u02d0' in position 28 when redirecting in WIndows

#73 mikedorin opened 2 years ago
0
Any way to add new languages?

#72 michaelpginn opened 2 years ago
0
Rename all "model" variables and modules with full names

#71 emersonknapp closed 1 year ago
1
Wave error for given sample

#70 sonal-ssj opened 2 years ago
0
Difference in outputs of splitted v/s unsplitted audio file

#69 007prateekd closed 2 years ago
2
make the output of "feature_window" function chronological

#68 padster06 opened 2 years ago
0
NumPy requirement is less than 1.22 and latest is 1.19.5

#67 SteveC00k opened 2 years ago
0
add emit_frame.py

#66 cckk2913 opened 2 years ago
0
Directory Name con not allowed on Windows

#65 steveway opened 2 years ago
1
Feature normalization can cause NaN to appear

#64 rcontrai opened 2 years ago
1
Unable to run interspeech21 model

#63 SlistInc opened 2 years ago
1
The timestamp of model 'interspeech21' is incorrect

#62 owaski opened 2 years ago
5
more model for recognition

#61 bongblender opened 2 years ago
1
Not able to transcribe simple word what in English

#60 FilBot3 closed 2 years ago
5
support for python 3.10

#59 bongblender opened 2 years ago
4
Optimizing for Latency

#58 mattare2 opened 2 years ago
0
Prior.txt file path

#57 Celine-Guan closed 2 years ago
2
The timestamp's duration always be 0.045

#56 z451538473 closed 2 years ago
2
Is the output phone or phonemes?

#55 raotnameh closed 2 years ago
2
maximum size for Inventory CustomizationIs?

#54 ElafIslam123 opened 2 years ago
1
Issue with using dependencies numpy with numba and panphon

#53 ytan101 closed 2 years ago
0
using 'eval' insted of 'distance' in trainer.py

#52 ElafIslam123 opened 2 years ago
1
请问没有中文语言的支持吗

#51 lvZic opened 2 years ago
4
recording best practice to get best result ?

#50 allan-simon opened 2 years ago
9
Any explanation on feature window re-ordering?

#49 Jackbennett opened 2 years ago
2
allosaurus results for Persian language

#48 sajede opened 3 years ago
2
pip download

#47 jacbrixey opened 3 years ago
4
add interspeech2021 compositional_phonetics model

#46 xinjli opened 3 years ago
0
Don't completely hide the download exception

#45 willstott101 closed 3 years ago
0
Remove duplicated resample_audio function

#44 willstott101 closed 3 years ago
1
Realtime? (low-latency streaming inference)

#43 willstott101 opened 3 years ago
5
tqdm required by prep_feat, prep_token

#42 zaidsheikh closed 3 years ago
1
Bypass the filename check when it is an instance of BytesIO objects

#41 kormoczi closed 3 years ago
1
How the different phonemes sounds exactly? (Preparation for fine-tuning...)

#40 kormoczi opened 3 years ago
11
Input wav file as a BytesIO object not working

#39 kormoczi closed 3 years ago
5
Phone duration is always 0.045

#38 artrayd opened 3 years ago
6
Issue with shapes alignment

#37 anushakabber closed 3 years ago
6
added the return_lstm and return_both options in the recognizer

#36 raotnameh closed 3 years ago
1
Option to extract last layer embeddings of the lstm.

#35 raotnameh closed 3 years ago
3
Loss for recognizing a part of audio

#34 Enternal17 opened 3 years ago
2
Cannot open 32 bit floating audio file

#33 freddy5566 opened 3 years ago
4
Phone distance metric

#32 mattare2 closed 3 years ago
3