Downloads · 30 days
58
22% of all-time downloads
luizhrocha/parakeet-tdt-0.6b-v3-ptBR-gguf
parakeet-tdt-0.6b-v3-ptBR-gguf is a automatic speech recognition model from luizhrocha. 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.
GGUF conversion of a Brazilian-Portuguese fine-tune of NVIDIA's parakeet-tdt-0.6b-v3, for CPU inference with parakeet.cpp.
Downloads · 30 days
58
22% of all-time downloads
All-time downloads
268
Public
Repo size
941 MB
Likes
0
Public
Click a slice to open those files.
.gguf941 MB · 100%
From the Hugging Face model README
GGUF conversion of a Brazilian-Portuguese fine-tune of NVIDIA's
parakeet-tdt-0.6b-v3, for CPU inference with
parakeet.cpp.
Converted with parakeet.cpp's own scripts/convert_parakeet_to_gguf.py.
No weights were retrained or altered — this is a format conversion only.
| file | quant | size |
|---|---|---|
ptbr-plus-q8_0.gguf | q8_0 | ~898 MB |
The stock parakeet-tdt-0.6b-v3 is multilingual on paper, but it takes no
language prompt — you cannot tell it what language it is hearing. It
auto-detects, and its detection is unreliable: on Portuguese audio it frequently
emits fluent, confident English. This is a known, unresolved upstream issue
(NVIDIA-NeMo/Speech#14799).
It is also span-dependent, which makes it especially treacherous. Measured on one 90-second pt-BR recording and a 25-second slice of that same audio:
tdt-v3, full 90s → "Marco 1. Eu começo a falar imediatamente, sem nenhuma pausa…" ✅ pt
tdt-v3, 25s slice → "Marco 2, esta is my voice and volume normal…" ❌ en
A pt-BR fine-tune cannot drift, because Portuguese is all it knows. The language is correct by construction rather than forced — and there is no flag to forget to set.
On a 90-second read pt-BR script (WER against the script; number words folded to
digits so "dois mil e vinte e seis" and "2026" compare equal):
| model | WER | pt-BR reliability | speed (CPU) | punctuation |
|---|---|---|---|---|
| this model | 12.7% | deterministic — cannot drift | ~9× realtime | yes |
tdt-0.6b-v3 | 13.3% | lottery — English on a short span | ~9× realtime | yes |
nemotron-3.5-asr-streaming-0.6b (forced pt) | 20.7% | deterministic | ~8× realtime | partial |
whisper small | 29.3% | deterministic | much slower on CPU | yes |
Single speaker, single recording — treat as indicative, not a benchmark.
parakeet-cli --model ptbr-plus-q8_0.gguf --decoder tdt audio.wav
No --lang needed (and none is honoured — TDT models take no prompt).
nvidia/parakeet-tdt-0.6b-v3 CC-BY-4.0
└─ alexandreacff/parakeet-tdt-0.6b-v3-ptBR-plus (fine-tune, pt-BR + podcasts,
│ punctuated + synthetic)
└─ this repo (GGUF format conversion only)
nvidia/parakeet-tdt-0.6b-v3 — CC-BY-4.0.alexandreacff/parakeet-tdt-0.6b-v3-ptBR-plus — all credit for the pt-BR adaptation goes to @alexandreacff.Licensing note, stated plainly: the fine-tune does not declare a license of its own. It is a derivative of a CC-BY-4.0 model, and this conversion is published under CC-BY-4.0 on that basis, with attribution to both authors above. If either author objects, open a discussion here and this repo will be taken down.
Converted for use in chimr, which needs correct Portuguese captions on CPU-only machines.