Automatic Speech Recognition
Transformers
NeMo
Safetensors
GGUF
PyTorch
parakeet_tdt
feature-extraction
speech
audio
Transducer
Transformer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Transformers
Eval Results (legacy)
Eval Results
Instructions to use nvidia/parakeet-tdt-0.6b-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/parakeet-tdt-0.6b-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nvidia/parakeet-tdt-0.6b-v3")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v3", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Japanese support plan?
#5
by sttt - opened
Excellent transcription model. Please support Japanese language so that I can switch from Whisper to this model.
Adding Japanese support would allow us to make subtitles for anime, movies, games and tv shows. Massively Bridging the gap for a lot of readily available media.
parakeet-tdt_ctc-0.6b-ja is only an ASR (automatic speech recognition) model — it takes Japanese audio → Japanese text.
no translation. yet. and worse yet no timestamps
Updates?
we need this
I would be so happy if we got a model that could do Japanese with timestamps.
Most open-source options like Whisper, VibeVoice-ASR and Qwen3-ASR have issues haven't pushed subtitle generation forward such as
- Not great accuracy
- Repetition
- Long random sections where speech isn't transcribed
- Off timings
- Timings being essentially "paragraph level" not sentence level (vibevoice I'm looking at you)