Mongolian Speech-to-Text Leaderboard
Whisper large-v3 MNOperating point: warmestman/whisper-large-v3-mn-cv-fleurs (Mongolian fine-tune) on mps

Whisper large-v3 MN — Mongolian Speech-to-Text Benchmark

Real results from the Whisper large-v3 MN Batch API (enhanced operating point, language mn) evaluated across 4 Mongolian datasets and 265 audio samples. Every number below is measured — not marketing. WER, speed, and pricing are shown as-is, brutally honest.

Language:MNDiarization:noneSamples:265Run:Aug 18, 2026, 11:25 PMEndpoint:local (transformers)
06710060.6%
Accuracy

265/265 samples transcribed · 100% success rate

06710039.4%
Word Error Rate

Lower is better · across 265 samples

Headline metrics
Character Error Rate14.9%
Avg speed factor1.57×realtime multiple
Total speed factor1.57×
Avg latency / sample4.5s
Total audio processed1849.3s30.8 min

Pricing

Whisper large-v3 MN list pricing for batch transcription. No discounts, no negotiated rates applied — the raw per-minute rate.

Per 1k minutes
$0
batch
Per minute
$0.0000
effective
Per 1k min (these 30.8 min)
$0.00
would cost
Open source?
proprietary

Pricing source: Whisper large-v3 MN public pricing. Duudlaga Flow is shown for context only — this page isolates Whisper large-v3 MN so the number is not padded by our own product.

WER & CER by dataset

Word and character error rates per dataset. Lower is better — and these are the real Whisper large-v3 MN numbers, which are weak on Common Voice 24.

Common Voice 24 (MN)
Source dataset →
WER
40.1%
CER
13.1%
Shunya Labs Mongolian Speech
Source dataset →
WER
28.6%
CER
8.8%
Common Voice 20 (MN)
Source dataset →
WER
41.3%
CER
15.8%
Modern Voice
WER
44.9%
CER
19.3%
WERCER

Dataset summary

Aggregate accuracy, speed, and timing for each dataset.

DatasetSourceSamplesSuccessWERCERAccuracySpeedAudio (s)Proc (s)
Common Voice 24 (MN)Hugging Face →5959/5940.1%13.1%59.9%1.51×330.6s218.4s
Shunya Labs Mongolian SpeechHugging Face →6060/6028.6%8.8%71.4%1.76×645.1s367.1s
Common Voice 20 (MN)Hugging Face →5454/5441.3%15.8%58.7%1.34×269.8s200.9s
Modern Voice9292/9244.9%19.3%55.1%1.56×603.8s388.2s

WER vs speed — per sample

Each dot is one audio sample. The sweet spot is the bottom-left (low error, fast). Whisper large-v3 MN sits high on error for many Common Voice 24 samples.

Per-sample results

Ground truth shown verbatim in the Expected column. The result column highlights only the words Whisper large-v3 MN got wrong, in red — no strikethrough/swap gymnastics, just the mistakes.

265 rows
redwrong word in the resultplaincorrectly transcribedExpected column shown verbatim as ground truth
#AudioSampleDatasetExpected (ground truth)Whisper large-v3 MN resultWERCERI/D/S
1btsee_0001Common Voice 24 (MN)Гэхдээ амьсгал хураахаасаа өмнө танд мэдэж байгаагаа хэлье.гэхдээ амьсгал хураахаасаа өмнө танд мэдэж байгаагаа хэлээ12.5%3.4%0/0/1
2btsee_0002Common Voice 24 (MN)Надад заяасан аз жаргал гэдэг ердөө гуравхан сарын хугацаатай байсан гэж үү?надад заяасан аж жаргал гэдэг эрдээ гуравхан сарын хугацаатай байсан гэж үү16.7%5.3%0/0/2
3btsee_0003Common Voice 24 (MN)Одоо бид өөрсдөө өвчин эмгэгээсээ салахыг хичээцгээе.одоо би дөөрч дөө өвчин эмгээгээсээ салахыг чивцгээв71.4%19.2%1/0/4
4btsee_0004Common Voice 24 (MN)Би бол голдуу хээрээр гэр, хэцээр дэр хийж явдаг хүн.би бол голдуу хээрээр гэр хэцээр дэрхий ч явдаг хүн20.0%5.9%0/0/2
5btsee_0005Common Voice 24 (MN)Хан хурмаст уурлаж, Болдоггүй Бор өвгөнийг хор луугаараа ниргүүлэхээр явуулжээ.ханхурамс дуурлас болдоггүй бороогүйн хоёр луугаар нэргүүлэхээр явуулжээ80.0%22.1%0/2/6
6btsee_0006Common Voice 24 (MN)Алив наашаа ороод ир гээд гэртээ оров.алив наашаа ороодор гээд гэртэй оров42.9%8.1%0/1/2
7btsee_0007Common Voice 24 (MN)Өө өндөр дээдэс таны тухайд би баталж чадахгүй.өө өндөр дээд таны тухайд би батал ч алдахгүй50.0%10.9%1/0/3
8btsee_0008Common Voice 24 (MN)Харин гурав дахь удаагаас эхлэн хүмүүсийг сонирхож эхлэв.харин гурав дахь удаагаас эхлэн хүмүүсийг сонирхож эхлэв0.0%0.0%0/0/0
9btsee_0009Common Voice 24 (MN)Та нар очингуутаа шөл л өгч үз.танар очингуутаа шөлөл өгчүүз85.7%10.0%0/3/3
10btsee_0010Common Voice 24 (MN)Ерөөсөө литр үйлдвэрээсээ салаагүй явсан юм чинь.ерөөсөө л үйлдвэрээсээ салаагүй явсан юм чинь14.3%6.2%0/0/1
Page 1 of 27

Methodology

How these numbers were produced.

Provider: Whisper large-v3 MN (Whisper large-v3 fine-tuned on Mongolian Common Voice 16.1 + FLEURS. Same author as the Common Voice 20 corpus in this benchmark, so its Common Voice scores should be read with train/test overlap in mind.). Models with this badge were trained on data that overlaps the benchmark corpora (Mongolian Common Voice — 113 of 173 samples — or the public Shunya Labs corpus). Scores on overlapping corpora are inflated by memorization; judge these models by the per-dataset table on their details page, especially the corpora they were NOT trained on.

Endpoint local (transformers). Language mn. Operating point warmestman/whisper-large-v3-mn-cv-fleurs (Mongolian fine-tune) on mps. Diarization none.

Datasets: Common Voice 24 (MN), Shunya Labs Mongolian Speech, Common Voice 20 (MN), Modern Voice — 265 samples, 1849.3s of audio total.

Dataset source URLs:

Metrics: WER and CER are computed with a standard word/character Levenshtein alignment, normalized for case and punctuation. Accuracy = 100 − WER. Speed factor = audio duration ÷ processing time (× realtime). All requests are real Whisper large-v3 MN Batch API calls, not cached or simulated.

Diff highlighting: The result column aligns to the ground truth and colors every substitution and insertion red. Deletions (words missing from the result) are not shown in the result column — the Expected column already holds the full ground truth as-is.

Generated by the Whisper large-v3 MN Benchmark Runner · Whisper large-v3 MN Batch API v2 · run Aug 18, 2026, 11:25 PM