- Giants
- Artificial Analysis
- Speech recognition error rates
Speech recognition error rates
Artificial Analysis's bar chart drew 15.3K views on X: 0.3x its typical post and #114 of 123 Artificial Analysis charts we track by views. Read Oct 10, 2026.
Cohere has released Cohere Transcribe: an open weights model achieving 4.7% on AA-WER, based on 3 datasets including our proprietary AA-AgentTalk dataset
Why it spread
The post spread because it landed on a hot topic that week and rode launch timing, with the account's 191 likes running far above its typical 16, alongside 11 reposts, 2 quotes, 64 saves and 15,303 views.
What worked
- The post tied a fresh model release to a ranked bar chart of speech recognition models by word error rate, giving readers an immediate comparison.
- It led with a concrete headline result, an open weights model at 4.7% on AA-WER across 3 datasets including a proprietary one, which made the claim feel specific and credible.
- It packed useful context into the text, naming the 2B parameter size, the conformer encoder-decoder architecture, training from scratch and 14 languages, so the chart had a story behind it.
What to borrow
We could pair our own chart with a timely launch or news hook, state one headline number up front, and describe the model setup in the caption so the ranking has context.
Careful
Do not over-read the spread as proof the chart design drove it, since the stated reasons were a hot topic that week and launch timing, and the quote rate sat in the bottom quarter while the source line was absent.
Written by our analysis model from the measured numbers above, not by Artificial Analysis.
Make it yours
Your numbers, in this bar chart.
Starts from the real numbers of "% of Artificial words transcribed incorrectly; lower is better. AA-WER v2.0 Index" by Artificial Analysis. Replace every number with yours before you post. Make one like this, step by step
Free pictures carry a small "Made with ViralChart" line. That line is how other people find us.
API · Max
Use this chart via API
On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id 0c01870a0fda.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/0c01870a0fda | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/0c01870a0fda/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/0c01870a0fda/render?view=1 | The draw-only view this page uses | Open |
| POST | /mcp | Tool get_chart_data with this id, for Claude, Cursor and other agents | Max |
curl -s https://viral-chart.com/api/v1/charts/0c01870a0fda/data \
-H "Authorization: Bearer $VIRALCHART_KEY"claude mcp add --transport http viralchart https://viral-chart.com/mcp \
--header "Authorization: Bearer $VIRALCHART_KEY"60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.
More from Artificial Analysis
All 123
Other giants using a bar chart
All 152
Questions people ask
How far did Artificial Analysis's "Speech recognition error rates" chart travel?
15,303 views, 191 likes, 11 reposts and 64 saves on X, read Oct 10, 2026. A normal post from @ArtificialAnlys gets about 54.2K views.
What kind of chart is it?
A bar chart. Ranking of speech recognition models by word error rate.
Can I use Artificial Analysis's chart?
Use the format, not the picture. The chart, logo and design belong to Artificial Analysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.