Armenian ASR (Yerevann)
Yerevann research lab Armenian speech recognition checkpoints.
Yerevann research lab Armenian speech recognition checkpoints.
Best for armenian-language transcription for journalism, civic tech, and accessibility projects. Pricing: free.
What it is
Yerevann is an Armenian machine-learning research group that has periodically released Armenian-language NLP and speech checkpoints. Armenian is another small-language gap in commercial STT, and these academic releases remain the most practical starting point for Armenian-language transcription. Buyers should pilot carefully on representative audio. Best fit when the buyer is armenian-language transcription for journalism, civic tech, and accessibility projects. The honest caveat: research-grade; quality on eastern vs western armenian varies. As with any open-weights release, the integrator owns hosting, scaling, and SLA — but the licensing cost is zero and the model can be fine-tuned on in-house audio.
Watch out for: Research-grade; quality on Eastern vs Western Armenian varies.
Install / use
huggingface.co/Yerevann or search 'armenian' for model cardsFeatures
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | No |
| Languages supported | 1 |
| HIPAA eligible | No |
Armenian ASR (Yerevann) vs Whipscribe
| Feature | Armenian ASR (Yerevann) | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | free beta |
| Speaker diarization | No | Yes |
| Word timestamps | No | Yes |
| Streaming | No | No |
| Languages | 1 | 99 |
| Platforms | Linux, macOS | Web, API, MCP |
Alternatives to Armenian ASR (Yerevann)
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.