Downloads · 30 days
57
14% of all-time downloads
Singla0009/Parakeet-TDT-0.6B-Japanese-GGUF
Parakeet-TDT-0.6B-Japanese-GGUF is a automatic speech recognition model from Singla0009. Use it when you need speech turned into text. It is set up for gguf. The card lists the license as cc-by-4.0.
This repository contains highly optimized GGUF versions of NVIDIA's parakeet-tdtctc-0.6b-ja Automatic Speech Recognition (ASR) model, specifically fine-tuned for the Japanese language.
Downloads · 30 days
57
14% of all-time downloads
All-time downloads
404
Public
Repo size
3.4 GB
Likes
1
Public
Click a slice to open those files.
.gguf3.4 GB · 100%
From the Hugging Face model README
This repository contains highly optimized GGUF versions of NVIDIA's parakeet-tdt_ctc-0.6b-ja Automatic Speech Recognition (ASR) model, specifically fine-tuned for the Japanese language.
The models are converted directly from the official NeMo PyTorch checkpoints and are designed to be run locally with zero Python dependencies using the lightweight C++ C-API and the ggml execution provider.
[!IMPORTANT] These GGUF models are fully metadata-driven. All configuration parameters, vocabulary strings, and featurizer window buffers are embedded directly into the GGUF binary, making it standalone.
| File | Precision | Size | Recommended For |
|---|---|---|---|
parakeet-tdt_ctc-0.6b-ja.f32.gguf | Float32 (Full) | ~2.49 GB | Maximum studio accuracy on GPU systems |
parakeet-tdt_ctc-0.6b-ja.q8_0.gguf | INT8 Quantized | ~884 MB | CPU-only inference & low-VRAM laptops |
[!TIP] Which one should I choose?
- If you have a dedicated NVIDIA GPU with 4+ GB VRAM, download the
f32file for maximum precision.- If you are running on a standard laptop (CPU only), a Mac, or a low-end GPU, download the
q8_0file. It uses 60% less RAM with practically zero accuracy loss.
Japanese is a notoriously complex language for Speech-to-Text systems due to its lack of spaces and the simultaneous use of three scripts (Kanji, Hiragana, and Katakana). This 600M parameter model was trained specifically to handle these phonetic and contextual complexities natively, resulting in flawless script generation across all three character sets.
[!IMPORTANT] CRITICAL EXECUTION REQUIREMENT: This model utilizes NVIDIA's advanced Token-and-Duration Transducer (TDT) architecture alongside CTC. To run this model in
parakeet-cli, you MUST specify the--decoder tdtflag. Using the standard CTC decoder will produce degraded results.
Benchmarks were performed locally on a Windows workstation running an NVIDIA GeForce RTX 5070 Ti GPU and an Intel CPU.
[!NOTE] For shorter clips (under 10 seconds), CPU is often slightly faster because it avoids the initial GPU kernel compilation and memory-transfer latency. On longer files (5+ minutes), GPU execution provides a massive speed improvement.
Unlike standard CTC (Connectionist Temporal Classification) or RNNT decoders, the Token-and-Duration Transducer (TDT) is a novel architecture invented by NVIDIA.
Instead of just predicting the next word, TDT models predict two things simultaneously:
By doing both at once, it allows the model to "skip" forward in the audio timeline, making transcription significantly faster and more accurate across varying speech tempos.
The original model architecture and weights were created and published by NVIDIA.
Both the source models and these converted GGUF files are released under the permissive Creative Commons Attribution 4.0 International (CC-BY-4.0).
This model was explicitly converted and optimized to be run inside RenderCaption — our custom desktop transcription software.
What is RenderCaption? RenderCaption is a fully offline, high-speed transcription application. It is built using Rust and Tauri, meaning it is incredibly lightweight, fast, and 100% private (no audio is ever sent to the cloud). Instead of writing Python code or using terminal commands, you can simply load this model into the RenderCaption desktop app and transcribe audio instantly with a beautiful user interface.
👉 Check out the RenderCaption Desktop App on GitHub Here!
To run these models via the command line, you need the parakeet-cli C++ execution engine.
parakeet-cli executable for your specific operating system (Windows/Linux/macOS).parakeet-cli transcribe --model parakeet-tdt_ctc-0.6b-ja.f32.gguf --input audio.wav --decoder tdt --lang ja
parakeet-cli transcribe --model parakeet-tdt_ctc-0.6b-ja.q8_0.gguf --input audio.wav --decoder tdt --lang ja