Speech to Text Recommendation: DeepSeek V3
Speech to Text → DeepSeek V3
Use Case Overview
DeepSeek V3 by Deepseek is a recommended option for the Speech to Text use case.
Recommended Models
| Rank | Vendor | Context Window | Score |
|---|
| #7 | Deepseek | 64K | 17/100 |
| Benchmark | Score |
|---|
| MMLU | 88.5 |
| HUMANEVAL | 82.6 |
| GSM8K | 89.3 |
| MATH | 61.6 |
| BBH | 84.9 |
Strengths
- MMLU score 88.5, strong knowledge reasoning.
- HumanEval 82.6, excellent code generation.
- GSM8K 89.3, robust math reasoning.
- Mixture-of-Experts architecture.
Requirements
- API key from deepseek
- Input length within 64K context window