Parakeet Tdt 0.6b v3 PtBR GGUF
GGUF conversion of a Brazilian-Portuguese fine-tune of NVIDIA's parakeet-tdt-0.6b-v3, for CPU inference with parakeet.cpp.
Modellquelle
- Art
- Other
- Dateigröße
- 897 MB
- Basismodell
- alexandreacff/parakeet-tdt-0.6b-v3-ptBR-plus
- Version
- vRevision 056f1fb
- Aktualisiert
- 27. Sept. 2026
- Downloads
- 37
- Quelle
- Hugging Face
Quellenbeschreibung
parakeet-tdt-0.6b-v3-ptBR — GGUF (for parakeet.cpp)
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 |
Why this exists
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.
Measurements
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.
Usage
parakeet-cli --model ptbr-plus-q8_0.gguf --decoder tdt audio.wav
No --lang needed (and none is honoured — TDT models take no prompt).
Provenance and licensing
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)
- Base model:
nvidia/parakeet-tdt-0.6b-v3— CC-BY-4.0. - Fine-tune:
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.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 30. Aug.
Modellartefakte
1 Artefakt
Modellartefakte
1 ArtefaktQuellenauszüge
2 Auszüge
Quellenauszüge
2 Auszüge--- license: cc-by-4.0 language: - pt library_name: gguf pipeline_tag: automatic-speech-recognition tags: - asr - speech-recognition - parakeet - parakeet.cpp - gguf - portuguese - pt-br base_model: alexandreacff/parakeet-tdt-0.6b-v3-ptBR-plus --- # parakeet-tdt-0.6b-v3-ptBR — GGUF (for parakeet.cpp) GGUF conversion of a **Brazilian-Portuguese fine-tune** of NVIDIA's `parakeet-tdt-0.6b-v3`, for CPU inference with [parakeet.cpp](https://github.com/mudler/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 | ## Why this exists 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](https://github.com/NVIDIA-NeMo/Speech/issues/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. ## Measurements 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. ## Usage ```bash parakeet-cli --model ptbr-plus-q8_0.gguf --decoder tdt audio.wav ``` No `--lan...
Source context: 37 downloads · 0 likes · Pipeline automatic-speech-recognition · Library gguf · Repo luizhrocha/parakeet-tdt-0.6b-v3-ptBR-gguf
