# Upload timeout / other ways to submit

**URL:** <https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322>\
**Category:** Children’s Speech Recognition Challenge\
**Created:** [February 3, 2026, 9:57pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322 "2026-02-03T21:57:40Z")\
**Posts on this page:** 13\
**Page:** 1

<div class="post-metadata">

**Author:** ![dmitry\_v](https://avatars.discourse-cdn.com/v4/letter/d/df705f/32.png) [@dmitry\_v](https://community.drivendata.org/u/dmitry_v)\
**Post date:** [February 3, 2026, 9:57pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/1 "2026-02-03T21:57:40Z")

</div>

My submission failed due to some network error, possibly because of my slow upload speed.

Could you please let me know:

- if there is an upload time limit on the website;
- if submissions are possible in a different way (via a CLI or API) instead of the web form?

---

<div class="post-metadata">

**Author:** ![setheggerrocks](https://avatars.discourse-cdn.com/v4/letter/s/ecb155/32.png) [@setheggerrocks](https://community.drivendata.org/u/setheggerrocks)\
**Post date:** [February 4, 2026, 2:54am UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/2 "2026-02-04T02:54:48Z")

</div>

How long was it running before it timed out? You need to have a solution that runs under 2 hours so if your internet speed is the problem then I am not sure the best solution. I had to use decent sized batches for my submission to work. It was my 22nd try and first success so good luck. I will try and keep watching the thread if you need any help. I have been trying since 6pm yesterday so I likely feel your frustration.

---

<div class="post-metadata">

**Author:** ![dmitry\_v](https://avatars.discourse-cdn.com/v4/letter/d/df705f/32.png) [@dmitry\_v](https://community.drivendata.org/u/dmitry_v)\
**Post date:** [February 4, 2026, 9:40am UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/3 "2026-02-04T09:40:54Z")

</div>

Thanks for your reply. I was referring only to the upload time, I wasn’t able to upload the solution at all, so no running time 🙂. I remember that in previous competitions people asked to increase the upload timeout from 1 to 3 hours.

BTW, what size was the model that were able to finish in 2 hours?

---

<div class="post-metadata">

**Author:** ![cszc](https://avatars.discourse-cdn.com/v4/letter/c/c68b51/32.png) [@cszc](https://community.drivendata.org/u/cszc)\
**Post date:** [February 4, 2026, 10:26pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/4 "2026-02-04T22:26:39Z")

</div>

> [@dmitry\_v](#):
>
> - if there is an upload time limit on the website;
> - if submissions are possible in a different way (via a CLI or API) instead of the web form?

Sorry you experienced this @dmitry_v ! Yes, the upload time limit was set to 1 hour. I’ve now upped it to **3 hours**. Hopefully that works for you. Unfortunately, there is not another way like a CLI or API to upload your submission.

---

<div class="post-metadata">

**Author:** ![dmitry\_v](https://avatars.discourse-cdn.com/v4/letter/d/df705f/32.png) [@dmitry\_v](https://community.drivendata.org/u/dmitry_v)\
**Post date:** [February 5, 2026, 10:49am UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/5 "2026-02-05T10:49:05Z")

</div>

Thank you! Yes, It helps

---

<div class="post-metadata">

**Author:** ![oknaitik](https://avatars.discourse-cdn.com/v4/letter/o/cc9497/32.png) [@oknaitik](https://community.drivendata.org/u/oknaitik)\
**Post date:** [February 7, 2026, 1:30pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/6 "2026-02-07T13:30:58Z")

</div>

Hello, did you encounter below issue during **smoke test**? I’ve tried using smaller hyperparameters to reduce the runtime but I’ve no clue what I could do. The logs are not very helpful either. If so, could you help?  
_Your submission timed out after running for too long on the execution platform. Reduce your runtime to the maximum allowed duration and try again._

---

<div class="post-metadata">

**Author:** ![oknaitik](https://avatars.discourse-cdn.com/v4/letter/o/cc9497/32.png) [@oknaitik](https://community.drivendata.org/u/oknaitik)\
**Post date:** [February 7, 2026, 4:26pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/7 "2026-02-07T16:26:31Z")

</div>

@cszc could you help in anyway?

---

<div class="post-metadata">

**Author:** ![dzunglt24](https://avatars.discourse-cdn.com/v4/letter/d/bb73d2/32.png) [@dzunglt24](https://community.drivendata.org/u/dzunglt24)\
**Post date:** [February 8, 2026, 2:51am UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/8 "2026-02-08T02:51:12Z")

</div>

Smoke test submission should take less than 4 or 5 minutes to run because it only run on 9000 examples.

So, the actual submission run on over 205000 examples can finish within 2hours.

---

<div class="post-metadata">

**Author:** ![cszc](https://avatars.discourse-cdn.com/v4/letter/c/c68b51/32.png) [@cszc](https://community.drivendata.org/u/cszc)\
**Post date:** [February 9, 2026, 4:17pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/9 "2026-02-09T16:17:59Z")

</div>

@dzunglt24 is correct, smoke tests should take less than 5 minutes to run. If it cannot run in that time, your full submission is unlikely to complete in the allotted 2 hours.

---

<div class="post-metadata">

**Author:** ![oknaitik](https://avatars.discourse-cdn.com/v4/letter/o/cc9497/32.png) [@oknaitik](https://community.drivendata.org/u/oknaitik)\
**Post date:** [February 10, 2026, 1:33pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/10 "2026-02-10T13:33:58Z")

</div>

Thank you for the confirmation!

Could you also confirm if all the test samples have correct `child_audio`→`label_text` mapping? You could ignore the noise/bg sounds here.

---

<div class="post-metadata">

**Author:** ![cszc](https://avatars.discourse-cdn.com/v4/letter/c/c68b51/32.png) [@cszc](https://community.drivendata.org/u/cszc)\
**Post date:** [February 10, 2026, 5:02pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/11 "2026-02-10T17:02:05Z")

</div>

Yes, test samples have the correct mapping. there may be some background noise, but those are not transcribed/included in the label text.

---

<div class="post-metadata">

**Author:** ![oknaitik](https://avatars.discourse-cdn.com/v4/letter/o/cc9497/32.png) [@oknaitik](https://community.drivendata.org/u/oknaitik)\
**Post date:** [February 12, 2026, 8:59am UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/12 "2026-02-12T08:59:51Z")

</div>

I’m assuming noisy-WER is solely on noisy samples. Could you also clarify if the public-WER is computed on both **noisy plus “traindata-like”** samples or just “traindata-like” samples?

---

<div class="post-metadata">

**Author:** ![cszc](https://avatars.discourse-cdn.com/v4/letter/c/c68b51/32.png) [@cszc](https://community.drivendata.org/u/cszc)\
**Post date:** [February 12, 2026, 5:24pm UTC](https://community.drivendata.org/t/upload-timeout-other-ways-to-submit/11322/13 "2026-02-12T17:24:03Z")

</div>

Yes, noisy-WER is evaluated solely on noisy samples. The public-WER may contain some samples with noise in it as well.
