Speech-to-text
Moonshine Base requirements, license & speed
By Moonshine AI (Useful Sensors) · released 2024-11-02 · 61M parameters
Commercial useYes
Min memoryNot stated
Runs on CPUYes
StreamingNo
Key facts
- License
- mit source
- Commercial use
- Yes sourceMIT for English; legacy non-English non-streaming models are non-commercial
- Parameters
- 61M source
- Minimum memory
- Not stated by source
- Runs on CPU
- Yes sourceDesigned for memory/compute-constrained platforms
- Streaming
- No sourceLegacy non-streaming model
- Voice cloning
- n/a (speech-to-text)
- Languages
- en source
- Released
- 2024-11-02 sourceHugging Face repo creation date (proxy for release date)
- Gated on HF
- No
Measured speed & memory
Benchmark pending. We haven't measured Moonshine Base yet. Planned targets: Raspberry Pi 5, CPU-only x86, Apple Silicon Mac and consumer GPUs. Get notified.
Accuracy
We don't run accuracy evals. For word error rate, check the Hugging Face Open ASR Leaderboard.
Similar STT models
Spotted an error? Report it. Every fact links to the model card or repo it came from.