58 lines
3.3 KiB
Markdown
58 lines
3.3 KiB
Markdown
# Parakeet and NeMo attribution
|
|
|
|
Pi Dictate uses NVIDIA's Parakeet-TDT 0.6B v3 model through NVIDIA NeMo. The repository does not redistribute the model weights. The installer downloads or copies the exact snapshot listed below.
|
|
|
|
## Model
|
|
|
|
- **Name:** `nvidia/parakeet-tdt-0.6b-v3`
|
|
- **Source:** <https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3>
|
|
- **Revision:** `541d1f99c6b0c3cd0b11a95167540bb8edefd82b`
|
|
- **Weight file:** `parakeet-tdt-0.6b-v3.nemo`
|
|
- **SHA-256:** `3cbdc85877e668ca7b82d0d56770eb1fac76691f55d6b97545e8d61ca588d10d`
|
|
- **License:** Creative Commons Attribution 4.0 International (CC BY 4.0), as stated by the model card
|
|
|
|
Users of the model must retain NVIDIA's attribution and comply with CC BY 4.0. Review the model card for intended use, limitations, and current license notices.
|
|
|
|
## Runtime
|
|
|
|
- **NVIDIA NeMo:** `nemo-toolkit[asr]` 3.0.0
|
|
- **Source:** <https://github.com/NVIDIA/NeMo>
|
|
- **License:** Apache License 2.0
|
|
- **Locally cached source used during implementation:** OpenSrc package `pypi:nemo-toolkit@3.0.0`
|
|
- **PyTorch:** 2.13.0 with CUDA 13.0 support
|
|
- **Python:** CPython 3.12
|
|
|
|
The complete transitive dependency versions and artifact hashes are recorded in `services/dictate/uv.lock`. Those dependencies retain their own licenses. Installing Pi Dictate does not change or replace their terms.
|
|
|
|
## Primary documentation
|
|
|
|
- NeMo ASR documentation: <https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/asr/intro.html>
|
|
- CC BY 4.0: <https://creativecommons.org/licenses/by/4.0/>
|
|
- Apache License 2.0: <https://www.apache.org/licenses/LICENSE-2.0>
|
|
|
|
## Optional cloud providers
|
|
|
|
Cloud backends are opt-in and are not required for local mode. Pi Dictate does not redistribute Meta or OpenAI models and does not include either provider's SDK. The host service sends audio only after the selected provider session is authenticated and ready. Provider terms, retention, security, and billing policies apply to cloud audio and any keyword or prompt context sent with it.
|
|
|
|
### Meta Model API Muse Voice Transcribe
|
|
|
|
- Announcement: <https://research.meta.ai/blog/introducing-muse-voice-transcribe>
|
|
- Speech-to-text guide: <https://ai.developer.meta.com/docs/speech-to-text>
|
|
- Realtime Voice API: <https://ai.developer.meta.com/docs/api-reference/voice/realtime>
|
|
- Voice event schemas: <https://ai.developer.meta.com/docs/api-reference/voice/schemas>
|
|
- Authentication: <https://ai.developer.meta.com/docs/getting-started/authentication>
|
|
- Meta terms: <https://ai.meta.com/terms/>
|
|
|
|
Pi Dictate uses only the documented `api.meta.ai` realtime endpoint and `muse-voice-transcribe-1.0` contract. It does not use the undocumented `shortwave.facebook.com` Muse Code endpoint.
|
|
|
|
### OpenAI Realtime transcription
|
|
|
|
- Realtime transcription guide: <https://developers.openai.com/api/docs/guides/realtime-transcription>
|
|
- Realtime WebSocket guide: <https://developers.openai.com/api/docs/guides/realtime-websocket>
|
|
- Speech-to-text guide: <https://developers.openai.com/api/docs/guides/speech-to-text>
|
|
- `gpt-live-transcribe` model: <https://developers.openai.com/api/docs/models/gpt-live-transcribe>
|
|
- OpenAI terms: <https://openai.com/policies/terms-of-use/>
|
|
- OpenAI privacy policy: <https://openai.com/policies/privacy-policy/>
|
|
|
|
The OpenAI default is `gpt-live-transcribe`; `gpt-transcribe` is a configurable commit-oriented alternative. `whisper-1` is not treated as a Realtime model.
|