Unverified50% confidenceBenchmarkExact time
Without fine-tuning, EmbeddingGemma-300M achieves only 51.7% to 60.8% recall@1 on the Belebele dataset for Tajik, Kazakh, Uzbek and Kyrgyz.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedCompared with monolingual models trained separately under the same settings, the unified model's recall@1 gap on Kazakh, Uzbek and Tajik is no more than 2.8 percentage points, and the confidence intervals for recall@10 overlap.68% similarUnverifiedIn TinyLlama's vocabulary, the codepoint coverage is 0% for Odia, 1% for Telugu, and 2% for Kannada.63% similarUnverifiedIn the KeyASRBench evaluation, the language-specific MER/WER range is 5.31% to 12.91%, while the KER range for the same set of systems is 13.61% to 33.81%.61% similarUnverifiedSaidzoda-CA-EmbeddingGemma-300M is a single multilingual embedding model fine-tuned from EmbeddingGemma-300M, serving four languages simultaneously: Tajik, Kazakh, Uzbek and Kyrgyz.60% similarUnverifiedUnder the Qwen3 tokenizer, Malayalam averages 13.47 tokens per word, while English averages 1.27 tokens per word.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1153277API
curl https://kongchang.com/api/v1/knowledge/claims/1153277MCP
get_claim(id=1153277)