Show HN: I trained a 9M speech model to fix my Mandarin tones

#1

Post by simedw » Sat, Jan 31, 2026, 12:51 AM UTC

Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes.

It's a 9M Conformer-CTC model trained on ~300h (AISHELL + Primewords), quantized to INT8 (11 MB), runs 100% in-browser via ONNX Runtime Web.

Grades per-syllable pronunciation + tones with Viterbi forced alignment.

Try it here: https://simedw.com/projects/ear/

Show HN: I trained a 9M speech model to fix my Mandarin tones
simedw.com

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#2

Post by jellojello » Sat, Jan 31, 2026, 1:25 AM UTC

This is amazing, if you feel like opening an entire language to being learned more easily.. Farsi is a VERY overlooked language, my wife/her family speak it but it's so difficult finding great language lessons (it's also called Persian/Dari)

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#3

Post by vunderba » Sat, Jan 31, 2026, 1:32 AM UTC

When I was living in Taiwan, one of the ways I forced myself to remember to pronounce the tones distinctly was by waving my hand in front of me, tracing the arc of each character’s tone.

It helped a lot even if I did look like an insane expat conducting an invisible orchestra.

One more thing: there's quite a bit of variation in how regional accents in the mainland can affect tonal pronunciation. It might be worth reaching to some native speakers to give you some baseline figures.

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#4

Post by rahimnathwani » Sat, Jan 31, 2026, 1:36 AM UTC

This is incredible. When I was first learning Chinese (casually, ~20 years ago), my teacher used some Windows software that drew a diagram of the shape of my pronunciation, so she could illustrate what I was getting wrong in some objective way.

The thing you've built is so good, and I would have loved to have it when I was learning Mandarin.

I tried it with a couple of sentences and it did a good job of identifying which tones were off.

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#5

Post by simedw » Sat, Jan 31, 2026, 1:37 AM UTC

jellojello wrote: post #2

This is amazing, if you feel like opening an entire language to being learned more easily.. Farsi is a VERY overlooked language, my wife/her family speak it but it's so difficult finding great language lessons (it's also called Persian/Dari)

Thank you.

I had a quick look at Farsi datasets, and there seem to be a few options. That said, written Farsi doesn’t include short vowels… so can you derive pronunciation from the text using rules?

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#6

Post by simedw » Sat, Jan 31, 2026, 1:45 AM UTC

vunderba wrote: post #3

When I was living in Taiwan, one of the ways I forced myself to remember to pronounce the tones distinctly was by waving my hand in front of me, tracing the arc of each character’s tone. It helped a lot even if I did look like an insane expat conducting an invisible orchestra. One more thing: there's quite a bit of variation in how regional accents in the mainland can affect tonal pronunciation. It might be worth rea…

For accents, I’ve mostly tested with a few friends so far. I’m wondering whether region should be a parameter, because training on all dialects might make the system too lax.

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#7

Post by drekipus » Sat, Jan 31, 2026, 1:48 AM UTC

instantly awesome.

I suck at chinese but I want to get better and I'm too embarassed to try and talk with real people and practise.

This is a great compromise. even just practising for a few minutes I already feel way more confident based on its feedback, and I feel like I know more about the details of pronunciation.

I'm worried this might get too big and start sucking like everything else.

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#8

Post by funkyfiddler369 » Sat, Jan 31, 2026, 1:55 AM UTC

[flagged]

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#9

Post by kranner » Sat, Jan 31, 2026, 1:55 AM UTC

simedw wrote: post #5

jellojello wrote: post #2

This is amazing, if you feel like opening an entire language to being learned more easily.. Farsi is a VERY overlooked language, my wife/her family speak it but it's so difficult finding great language lessons (it's also called Persian/Dari)

Thank you. I had a quick look at Farsi datasets, and there seem to be a few options. That said, written Farsi doesn’t include short vowels… so can you derive pronunciation from the text using rules?

> written Farsi doesn’t include short vowels… so can you derive pronunciation from the text using rules?

You can't, but Farsi dictionaries list the missing short vowels/diacritics/"eraab" for every word.

For instance, see this entry: https://vajehyab.com/dehkhoda/%D8%AD%D8%B3%D8%A7%D8%A8?q=%D8...

With the short vowel on the first letter it would be written حِساب (normally written as just حساب)

The dictionary entry linked shows that there is a ِ on the first letter ح

But you would have to disambiguate between homographs that differ only in the eraab.

Re: Show HN: I trained a 9M speech model to fix my Mandarin tones

#10

Post by btrlsnqtn » Sat, Jan 31, 2026, 2:00 AM UTC

The article mentions the bitter lesson. I'm confused about the status of Sutton's opinion of the bitter lesson. On the one hand, he invented the concept. On the other hand, he appears to be saying that LLMs are not the correct approach to artificial intelligence, which to a naive outsider looks like a contradiction. What gives?