text
stringlengths 526
3.89k
|
|---|
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
yan is far ms on the top of a mountain<\ph>y ae n ih z f aa r m ih z aa n dh ah t aa p ah v ah m aw n t ah n
### Response:
yannis farm is on the top of a mountain |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
lived<\ph>l ay v d
### Response:
live |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
haise vavision of hommes in his reging up in an arch chair with his black clay between his flips ups his winps<\ph>hh ey z v ah v ih zh ah n ah v hh aa m z ih n hh ih z r iy jh ih ng ah p ih n ae n aa r ch ch eh r w ih dh hh ih z b l ae k k l ey b ih t w iy n hh ih z f l ih p s ah p s hh ih z w ih n p s
### Response:
haze vague vision of holmes in his dressinggown coiled up in an armchair with his black clay pipe between his lips |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tripped amorrow<\ph>t r ih p t ae m er ow
### Response:
trip tomorrow |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
mast<\ph>m ae s t
### Response:
must |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
asling seem<\ph>ah s l ih ng s iy m
### Response:
aisling seems |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
at breaed<\ph>ae t b r iy d
### Response:
ate bread |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
wen<\ph>w eh n
### Response:
when |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
crimarate is rising steadely<\ph>k r ih m ah r ey t ih z r ay z ih ng s t eh d ah l iy
### Response:
crime rate is rising steadily |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
merry<\ph>m eh r iy
### Response:
mary |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tames signnature<\ph>t ey m z s ih g n ah ch er
### Response:
toms signature |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
doors<\ph>d ao r z
### Response:
door |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
sir priight tom<\ph>s er p r ay t t aa m
### Response:
surprise tom |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
felt aria word<\ph>f eh l t aa r iy ah w er d
### Response:
felt reassured |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
timesaid i yes i knew him well in fact he was an old sutor of mine<\ph>t ay m s ey d ay y eh s ay n uw hh ih m w eh l ih n f ae k t hh iy w aa z ae n ow l d s uw t er ah v m ay n
### Response:
time said i yes i knew him well in fact he was an old suitor of mine |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
too<\ph>t uw
### Response:
to |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
sequly dimore fixand trns o means those stretural those stristructures resemble their gender more than their sensitive ed secu<\ph>s iy k l iy d ih m ao r iy f ih k s ah n d t r eh n z ow m iy n z dh ow z s t r eh ch er ah l dh ow z s t r ih s t r ah k s t uh r z ih z r ih z eh m b ah l dh eh r jh eh n d er m ao r dh ae n dh eh r s eh n s ah t ih v eh d s eh k uw
### Response:
sexually dimorphic and trans individuals prior to any hormones those structures resemble their gender more than their assigned sex |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
merers sole<\ph>m eh r er z s ow l
### Response:
mirrors soul |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
their<\ph>dh eh r
### Response:
there |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
marry diying<\ph>m eh r iy d ay ih ng
### Response:
mary dying |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
memwere more like you<\ph>m eh m w eh r m ao r l ay k y uw
### Response:
mary were more like you |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
ot<\ph>ao t
### Response:
that |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
adog<\ph>ah d ao g
### Response:
a dog |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
ifal outer the luvre um useum<\ph>ay f ah l aw t er dh ah l ah v er ah m y uw s uw m
### Response:
eiffel tower the louvre museum |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tats me<\ph>t ae t s m iy
### Response:
tom mary |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
laves<\ph>l ey v z
### Response:
loves |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
find<\ph>f ay n d
### Response:
fine |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
manhas ten fingers<\ph>m ae n hh ah z t eh n f ih ng g er z
### Response:
man has ten fingers |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
nsty<\ph>s t ay n iy
### Response:
nasty |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
we<\ph>w iy
### Response:
why |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
special sts are quite enough<\ph>s p eh sh ah l s t iy eh n s iy aa r k w ay t ih n ah f
### Response:
specialists are quite enough |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
cart garfy for the fantisy<\ph>k aa r t g aa r f iy f ao r dh ah f ae n t iy z
### Response:
cartography for the fantasy book |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
only<\ph>ow n l iy
### Response:
lonely |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
serious bear<\ph>s ih r iy ah s b eh r
### Response:
ziri bare |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
broother<\ph>b r uw dh er
### Response:
brother |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
fulme<\ph>f uh l m
### Response:
fool me |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tathsaid that he regrets not studying french harder when he was in high school<\ph>t ae th s t ey dh ae t hh iy r ih g r eh t s n aa t s t ah d iy ih ng f r eh n ch hh aa r d er w eh n hh iy w aa z ih n hh ay s k uw l
### Response:
tom said that he regrets not studying french harder when he was in high school |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
remaers<\ph>r iy m er z
### Response:
remains |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
marde comes<\ph>m aa r d k ah m z
### Response:
married cousins |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
free unyens<\ph>f r iy y uw n y ah n z
### Response:
fry onions |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
taom<\ph>t aa m
### Response:
tom |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
guide book this is the best resterter on around here<\ph>g ay d b uh k dh ih s ih z dh ah b eh s t r eh s t er t er aa n er aw n d hh iy r
### Response:
guidebook this is the best restaurant around here |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tuby us screamed at the guy that police were on the way<\ph>t uw b iy ah s s k r iy m d ae t dh ah g ay dh ae t p ah l iy s w er aa n dh ah w ey
### Response:
tobias screamed at the guy that police were on the way |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
hereat in home than the one spoken in the region where they live and are typically capable in both though their strength in each language speakers<\ph>hh ih r ah t ih n hh ow m dh ae n dh ah w ah n s p ow k ah n ih n dh ah r iy jh ah n w eh r dh ey l ay v ah n d aa r t ih p ih k l iy k ey p ah b ah l ih n b ow th dh ow dh eh r s t r eh ng k th ih n iy ch l ae ng g w ah jh s p iy k er z
### Response:
heritage learn at home than the one spoken in the region where they live and are typically capable in both though their strength in each language varies |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
jon staach<\ph>jh aa n s t aa ch
### Response:
john statue |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
merty vited<\ph>m er t iy v ay t ih d
### Response:
mary invited |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tams merisent<\ph>t ae m z m eh r ih s ah n t
### Response:
tom mary isnt |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
bar o your pen<\ph>b aa r ow y ao r p eh n
### Response:
borrow your pen |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
polial<\ph>p aa l iy ah l
### Response:
police |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
mery<\ph>m eh r iy
### Response:
mary |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
fifty lost its lives<\ph>f ih f t iy l ao s t ih t s l ih v z
### Response:
fig tree lost its leaves |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
yor<\ph>y ao r
### Response:
your |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
popoint<\ph>p ah p oy n t
### Response:
point |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
mer<\ph>m eh r
### Response:
mary |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
some one kisting tom<\ph>s ah m w ah n k ih s t ih ng t aa m
### Response:
someone kissing tom |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
manufacturing behind the gate gazing at the house<\ph>m ae n y ah f ae k ch er ih ng b ih hh ay n d dh ah g ey t g ey z ih ng ae t dh ah hh aw s
### Response:
man stood behind the gate gazing at the house |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tamdid not have enough money to buy food for everybody<\ph>t ae m d ih d n aa t hh ae v ih n ah f m ah n iy t uw b ay f uw d f ao r eh v r iy b aa d iy
### Response:
tom did not have enough money to buy food for everybody |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
ride<\ph>r ay d
### Response:
cried |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
st would behind me<\ph>s t r iy t w uh d b ih hh ay n d m iy
### Response:
stood behind me |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
sers<\ph>s er z
### Response:
sources |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
good clena etist<\ph>g uh d k l iy n ah eh t ih s t
### Response:
good clarinetist |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
sison<\ph>s ih s ah n
### Response:
license |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
zireburst in the room and saved rima<\ph>z ay r b er ah s t ih n dh ah r uw m ah n d s ey v d r iy m ah
### Response:
ziri burst in the room and saved rima |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
stake case is very heavy<\ph>s t ey k k ey s ih z v eh r iy hh eh v iy
### Response:
suitcase is very heavy |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
recless<\ph>r ih k l eh s
### Response:
reckless |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
gans<\ph>g ae n z
### Response:
guns |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
isee you have made a friend<\ph>ay z ey y uw hh ae v m ey d ah f r eh n d
### Response:
i see you have made a friend |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
department meeting relations with time on<\ph>d ih p aa r t m ah n t m iy t ih ng r iy l ey sh ah n z w ih dh t ay m aa n
### Response:
diplomatic relations with taiwan |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
merreis not as bad as you say she is<\ph>m eh r iy z n aa t ae z b ae d ae z y uw s ey sh iy ih z
### Response:
mary is not as bad as you say she is |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
you are im barus ing<\ph>y uw aa r ih m b aa r ah s ih ng
### Response:
you are embarrassing |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
ill ect triwerers are heated by electricity<\ph>ih l eh k t t r ih w er er z aa r hh iy t ah d b ay ih l eh k t r ih s ah t iy
### Response:
electric irons are heated by electricity |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tamcould not figure it out<\ph>t ae m k aw l d n aa t f ih g y er ih t aw t
### Response:
tom could not figure it out |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
yanyweres a six<\ph>y eh n y w eh r z ah s ih k s
### Response:
yanni wears a six |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
a warded to the lowest bider<\ph>ah w ao r d ih d t uw dh ah l ow ah s t b ay d er
### Response:
awarded to the lowest bidder |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
yan e apse five times a day<\ph>y ae n iy ae p s f ay v t ay m z ah d ey
### Response:
yanni prays five times a day |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
was defend her self<\ph>w aa z d ih f eh n d hh er s eh l f
### Response:
was defending herself |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tams<\ph>t ae m z
### Response:
tom |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tomis not always as busy as he says he is e is he is<\ph>t ow m ih s n aa t ao l w ey z ae z b ih z iy ae z hh iy s eh z hh iy ih z iy ih z hh iy ih z
### Response:
tom is not always as busy as he says he is |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
write<\ph>r ay t
### Response:
right |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
poliesmin<\ph>p ow l iy z eh m ih s
### Response:
policemen |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
ding tam a balance is in india<\ph>d ih ng t ae m ah b ae l ah n s ih z ih n ih n d iy ah
### Response:
building taj mahal is in india |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
mare<\ph>m eh r
### Response:
mary |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tamass<\ph>t ey m ah s
### Response:
thomas |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
surgerye<\ph>s er jh er iy
### Response:
surgery |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
type swell<\ph>t ay p s w eh l
### Response:
types well |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
easily li<\ph>iy z ah l iy l iy
### Response:
easily |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
e that even a child can read it<\ph>iy dh ae t iy v ih n ah ch ay l d k ae n r eh d ih t
### Response:
that even a child can read it |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
very supporte vis<\ph>v eh r iy s ah p ao r t v ih s
### Response:
very supportive |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
timedily<\ph>t ay m d iy l iy
### Response:
immediately |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
taomand merary are up to something<\ph>t aw m ah n d m eh r er iy aa r ah p t uw s ah m th ih ng
### Response:
tom and mary are up to something |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
wanted<\ph>w aa n t ah d
### Response:
want |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
re ining for a week<\ph>r ey ih n ih ng f ao r ah w iy k
### Response:
raining for a week |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
e pil have stadde the heavenes first with simple visual tha appropriate tell as stle us coplors<\ph>iy p ih l hh ae v s t ae d dh ah hh eh v ah n iy z f er s t w ih dh s ih m p ah l v ih zh ah w ah l dh ey ah p r ow p r iy ah t t eh l ae z s t iy l ey ah s k aa p l er z
### Response:
people have studied the heavens first with simple visual observation the aid telescopes and binoculars |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tammand meri said jon was not at home when they went to visit im<\ph>t ae m ah n d m eh r iy s eh d jh aa n w aa z n aa t ae t hh ow m w eh n dh ey w eh n t t uw v ih z ah t ih m
### Response:
tom and mary said john was not at home when they went to visit him |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
wanted<\ph>w aa n t ah d
### Response:
want |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
same selped carand he smelt so bad<\ph>s ey m s eh l p t k eh r ah n d hh iy s m eh l t s ow b ae d
### Response:
sami slept car and he smelt so bad |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
of sina mon<\ph>ah v s iy n ah m ow n
### Response:
of cinnamon |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
mery ar<\ph>m eh r iy aa r
### Response:
mary are |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
at a turk cannot stand when some one talks about the armenan gena side<\ph>ae t ah t er k k ae n aa t s t ae n d w eh n s ah m w ah n t ao k s ah b aw t dh ah aa r m ah n ah n jh eh n ah s ay d
### Response:
ataturk cannot stand when someone talks about the armenian genocide |
Below is an instruction that describes a task, paired with input that provides further context. Write a response that appropriately completes the request.
### Instruction:
You are an ASR transcript corrector. You have a transcript generated by an automatic speech recognition model, and their corresponding phoneme representations seperated by <\ph>. Your task is to generate the most accurate and coherent transcript that is free from grammatical or logical or lexical or phonetic errors.
### Input:
tams<\ph>t ae m z
### Response:
toms |