---
license: apache-2.0
language:
  - et
tags:
  - asr
  - speech
  - coreml
  - nemo
  - parakeet
  - yuriyvnv
  - 6bit-palettize-kmeans
library_name: coremltools
pipeline_tag: automatic-speech-recognition
base_model: yuriyvnv/parakeet-tdt-0.6b-estonian
---

# parakeet-tdt-0.6b-estonian-coreml-6bit

CoreML conversion of [yuriyvnv/parakeet-tdt-0.6b-estonian](https://huggingface.co/yuriyvnv/parakeet-tdt-0.6b-estonian) — 6BIT PALETTIZE KMEANS quantized.

| | |
|---|---|
| **Architecture** | TDT (Token-and-Duration Transducer) |
| **Language** | Estonian |
| **Sample rate** | 16000 Hz |
| **Max audio** | 15.0s |
| **Vocab size** | 8192 |
| **Framework** | NVIDIA NeMo → CoreML (coremltools) |

## Components

| File | Component | Best compute |
|------|-----------|--------------|
| `parakeet_mel_encoder.mlpackage` | mel_encoder | ANE / GPU |
| `parakeet_decoder.mlpackage` | decoder | CPU only |
| `parakeet_joint_decision_single_step.mlpackage` | joint_decision_single_step | ANE / GPU |

## Usage

```bash
pip install ovos-stt-plugin-coreml
```

```python
from ovos_stt_plugin_coreml import CoremlSTT
from ovos_plugin_manager.utils.audio import AudioFile

stt = CoremlSTT(config={"metadata": "metadata.json"})

with AudioFile("speech.wav") as f:
    audio = f.read()
print(stt.execute(audio))
```

## Source model

[yuriyvnv/parakeet-tdt-0.6b-estonian](https://huggingface.co/yuriyvnv/parakeet-tdt-0.6b-estonian)