Mozilla Luganda Automatic Speech Recognition
Can you create an Automatic Speech Recognition model for Luganda?
Prize
$3 000 USD
Time
Ended ~1 year ago
Participants
20 active · 160 enrolled
Helping
Uganda
Advanced
Automatic Speech Recognition
Natural Language Processing
Description

Voice recognition technologies can make services more accessible and more human. But the problem is that automatic speech recognition (ASR) requires enormous amounts of voice data.

There have been many advances in data collection and Automatic Speech Recognition (ASR) methodologies in recent years, which are revolutionizing the possibilities in this area especially for under-resourced languages in Africa.

The objective of this challenge is to build a machine learning ASR model to accurately recognize words spoken in Luganda.

You are encouraged to use the resources available to you from NVIDIA, such as NVIDIA NeMo ASR and documentation on NVIDIA ASR. You can also use transfer learning using the Kinyarwanda language datasets available on Mozilla Common Voice, and any other open-source models and libraries.

A more accurate ASR model for Luganda could lead to new mobile applications and other products and services that better serve Lugandan speakers. From transportation and healthcare to financial services and education, voice recognition for under-resourced languages has the potential to change the daily realities for millions of people.

To be eligible to win the NVIDIA and GTC prizes, you must register for GTC before 31 October 2021. You can register here.

The dataset has been made possible through the work of Makerere AI lab. The lab  is working towards building a Luganda data set through the Common Voice platform as part of their work of building NLP text and speech data set for low resourced languages in East Africa.

Mozilla Common Voice is an initiative to help teach machines how real people speak. This project is an effort to bridge the digital speech divide. Voice recognition technologies bring a human dimension to our devices, but developers need an enormous amount of voice data to build them. Currently, most of that data is expensive and proprietary. Mozilla Common Voice makes voice data freely and publicly available, and makes sure the data represents the diversity of real people across Africa and around the world.

The Mozilla Common Voice platform currently hosts a 2GB Luganda dataset with 80 hours of audio and a 54 GB Kinyarwanda dataset with 2,255 hours of audio.

About NVIDIA GTC (nvidia.com/gtc)

NVIDIA GTC is more than a must-attend AI conference for developers. It’s a global experience that brings together thousands of innovators, researchers, thought leaders, and decision-makers who are shaping our world with the power of AI, computer graphics, data science, and more. Register and join free online 8-11 November 2021.

Be sure the check out these relevant sessions:

9 November 2021: Finding Your True Voice AI: Breaking Language Barriers with Natural Language Processing [A31125]

10 November 2021: Bridging the Last Mile Gap with AI Education [A31127]

Other useful links to GTC:

  1. nvidia.com/gtc
  2. Sessions on AI
  3. Sessions on computer graphics
  4. Sessions on data science
  5. Emerging Chapters Education
Rules

Teams and collaboration

You may participate in competitions as an individual or in a team of up to four people. When creating a team, the team must have a total submission count less than or equal to the maximum allowable submissions as of the formation date. A team will be allowed the maximum number of submissions for the competition, minus the total number of submissions among team members at team formation. Prizes are transferred only to the individual players or to the team leader.

Multiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be immediately disqualified from the platform.

Code must not be shared privately outside of a team. Any code that is shared, must be made available to all competition participants through the platform. (i.e. on the discussion boards).

The Zindi user who sets up a team is the default Team Leader. The Team Leader can invite other data scientists to their team. Invited data scientists can accept or reject invitations. Until a second data scientist accepts an invitation to join a team, the data scientist who initiated a team remains an individual on the leaderboard. No additional members may be added to teams within the final 5 days of the competition or the last hour of a hackathon, unless otherwise stated in the competition rules

A team can be disbanded if it has not yet made a submission. Once a submission is made individual members cannot leave the team.

All members in the team receive points associated with their ranking in the competition and there is no split or division of the points between team members.

Datasets and packages

The solution must use publicly-available, open-source packages only.

You may only use version 7.0 or previous versions for training.

You may use only the datasets provided for this competition. Automated machine learning tools such as automl are not permitted.

You may use pretrained models as long as they are openly available to everyone.

You are allowed to access, use and share competition data for any commercial,. non-commercial, research or education purposes, under a CC-BY SA 4.0 license.

You must notify Zindi immediately upon learning of any unauthorised transmission of or unauthorised access to the competition data, and work with Zindi to rectify any unauthorised transmission or access.

Your solution must not infringe the rights of any third party and you must be legally entitled to assign ownership of all rights of copyright in and to the winning solution code to Zindi.

Submissions and winning

You may make a maximum of 10 submissions per day.

You may make a maximum of 300 submissions for this competition.

Before the end of the competition you need to choose 2 submissions to be judged on for the private leaderboard. If you do not make a selection your 2 best public leaderboard submissions will be used to score on the private leaderboard.

Zindi maintains a public leaderboard and a private leaderboard for each competition. The Public Leaderboard includes approximately 20% of the test dataset. While the competition is open, the Public Leaderboard will rank the submitted solutions by the accuracy score they achieve. Upon close of the competition, the Private Leaderboard, which covers the other 80% of the test dataset, will be made public and will constitute the final ranking for the competition.

Note that to count, your submission must first pass processing. If your submission fails during the processing step, it will not be counted and not receive a score; nor will it count against your daily submission limit. If you encounter problems with your submission file, your best course of action is to ask for advice on the Competition’s discussion forum.

If you are in the top 20 at the time the leaderboard closes, we will email you to request your code. On receipt of email, you will have 48 hours to respond and submit your code following the submission guidelines detailed below. Failure to respond will result in disqualification.

If your solution places 1st, 2nd, or 3rd on the final leaderboard, you will be required to submit your winning solution code to us for verification, and you thereby agree to assign all worldwide rights of copyright in and to such winning solution to Zindi.

If two solutions earn identical scores on the leaderboard, the tiebreaker will be the date and time in which the submission was made (the earlier solution will win).

If the error metric requires probabilities to be submitted, do not set thresholds (or round your probabilities) to improve your place on the leaderboard. In order to ensure that the client receives the best solution Zindi will need the raw probabilities. This will allow the clients to set thresholds to their own needs.

The winners will be paid via bank transfer, PayPal, or other international money transfer platform. International transfer fees will be deducted from the total prize amount, unless the prize money is under $500, in which case the international transfer fees will be covered by Zindi. In all cases, the winners are responsible for any other fees applied by their own bank or other institution for receiving the prize money. All taxes imposed on prizes are the sole responsibility of the winners. The top 3 winners or team leaders will be required to present Zindi with proof of identification, proof of residence and a letter from your bank confirming your banking details.Winners will be paid in USD or the currency of the competition. If your account cannot receive US Dollars or the currency of the competition then your bank will need to provide proof of this and Zindi will try to accommodate this.

Payment will be made after code review and an introductory call with the host.

You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these rules. Entry into this competition constitutes your acceptance of these official competition rules.

Zindi is committed to providing solutions of value to our clients and partners. To this end, we reserve the right to disqualify your submission on the grounds of usability or value. This includes but is not limited to the use of data leaks or any other practices that we deem to compromise the inherent value of your solution.

Zindi also reserves the right to disqualify you and/or your submissions from any competition if we believe that you violated the rules or violated the spirit of the competition or the platform in any other way. The disqualifications are irrespective of your position on the leaderboard and completely at the discretion of Zindi.

Please refer to the FAQs and Terms of Use for additional rules that may apply to this competition. We reserve the right to update these rules at any time.

Reproducibility of submitted code

  • If your submitted code does not reproduce your score on the leaderboard, we reserve the right to adjust your rank to the score generated by the code you submitted.
  • If your code does not run you will be dropped from the top 10. Please make sure your code runs before submitting your solution.
  • Always set the seed. Rerunning your model should always place you at the same position on the leaderboard. When running your solution, if randomness shifts you down the leaderboard we reserve the right to adjust your rank to the closest score that your submission reproduces.
  • We expect full documentation. This includes:
  • All data used
  • Output data and where they are stored
  • Explanation of features used
  • A requirements file with all packages and versions used
  • Your solution must include the original data provided by Zindi and validated external data (if allowed)
  • All editing of data must be done in a notebook (i.e. not manually in Excel)
  • Environment code to be run. (e.g. Google Colab or the specifications of your local machine)
  • Expected run time for each notebook. This will be useful to the review team for time and resource allocation.

Data standards:

  • Your submitted code must run on the original train, test, and other datasets provided.
  • If external data is allowed, external data must be freely and publicly available, including pre-trained models with standard libraries. If external data is allowed, any data used should be shared with Zindi to be approved and then shared on the discussion forum. Zindi will also make note of the external data available on the data page.
  • Packages:
  • You must submit a requirements file with all packages and versions used.
  • If a requirements file is not provided, solutions will be run on the most recent packages available.
  • Custom packages in your submission notebook will not be accepted.
  • You may only use tools available to everyone i.e. no paid services or free trials that require a credit card.

Consequences of breaking any rules of the competition or submission guidelines:

  • First offence: No prizes for 6 months and 2000 points will be removed from your profile (probation period). If you are caught cheating, all individuals involved in cheating will be disqualified from the challenge(s) you were caught in and you will be disqualified from winning any competitions for the next six months and 2000 points will be removed from your profile. If you have less than 2000 points to your profile your points will be set to 0.
  • Second offence: Banned from the platform. If you are caught for a second time your Zindi account will be disabled and you will be disqualified from winning any competitions or Zindi points using any other account.
  • Teams with individuals who are caught cheating will not be eligible to win prizes or points in the competition in which the cheating occurred, regardless of the individuals’ knowledge of or participation in the offence.
  • Teams with individuals who have previously committed an offence will not be eligible for any prizes for any competitions during the 6-month probation period.

Monitoring of submissions

  • We will review the top 20 solutions of every competition when the competition ends.
  • We reserve the right to request code from any user at any time during a challenge. You will have 24 hours to submit your code following the rules for code review (see above). Zindi reserves the right not to explain our reasons for requesting code. If you do not submit your code within 24 hours you will be disqualified from winning any competitions or Zindi points for the next six months. If you fall under suspicion again and your code is requested and you fail to submit your code within 24 hours, your Zindi account will be disabled and you will be disqualified from winning any competitions or Zindi points with any other account.
Evaluation

The evaluation metric for this challenge is Word Error Rate Metric.

You can read more about WER in this medium article. Here are some libraries to start off with.

For every row in the dataset, submission files should contain 2 columns: ID and Target.

Your submission file should look like this:

Audio_ID     Target        
ID_8CVQ0A4K  Omuserikale akulira disitulikiti yakirizza okulondoola ebyaliwo
ID_PGI8EFYS  Osobola okumpandiikira ekintu kyonna ky'oyagala nze ne nkikuwa                   
Prizes

1st place: $1 500

2nd place: $900

3rd place: $600

Bonus NVIDIA Prizes: The top 5 solutions received by 31 October 2021 11:59 PM GMT will win:

1. A voucher to attend a special INSTRUCTOR-LED WORKSHOP at the GTC: Building Transformer-Based Natural Language Processing Applications. (A value of $500 per voucher.)

2. A Jetson Nanos Developer Kit

If the winner is unable to attend the workshop at the GTC, we reserve the right to award the voucher to the next winner.

To be eligible to win the NVIDIA prizes, you must register for the GTC by 31 October 2021. You can register here.

Timeline

Competition closes on 16 January 2022.

Final submissions must be received by 11:59 PM GMT.

We reserve the right to update the contest timeline if necessary.