Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text to speech

orpheus-3b-ptbr-lora

by Lumazini Code Lumazini-Code/orpheus-3b-ptbr-lora

orpheus-3b-ptbr-lora is an open-weight model for text to speech from Lumazini Code, released under Apache License 2.0. Its published files total 27.9 GB.

opedromartins/ASR-datasets-ptbr - freds0/TAGARELA basemodel: - canopylabs/orpheus-3b-0.1-ft pipelinetag: text-to-speech - text-to-speech - tts - orpheus - lora - unsloth - snac - portuguese - brazilian-portuguese - llama.cpp

Parameters—
Context—
Weights27.9 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Lumazini Code, published under apache-2.0, revision 67516d81e9ca.

opedromartins/ASR-datasets-ptbr - freds0/TAGARELA basemodel: - canopylabs/orpheus-3b-0.1-ft pipelinetag: text-to-speech - text-to-speech - tts - orpheus - lora - unsloth - snac - portuguese - brazilian-portuguese - llama.cpp

Read Lumazini Code's full model card

license: apache-2.0 datasets: - opedromartins/ASR-datasets-ptbr - freds0/TAGARELA language: - pt base_model: - canopylabs/orpheus-3b-0.1-ft pipeline_tag: text-to-speech tags: - text-to-speech - tts - orpheus - lora - unsloth - snac - portuguese - brazilian-portuguese - llama.cpp

Identity and Version

Repository
Lumazini-Code/orpheus-3b-ptbr-lora
Publisher
Lumazini Code
Task
Text to speech
Modality
Audio
Library
Not stated by the source
Parameters
Not stated by the source
Languages
pt
Revision
67516d81e9ca5fa96b93131195fc00bab1133c7a
First published
2026-09-19
Last updated
2026-09-21

Files and Weights

92 files, 27.9 GB in total. The weights are 63 files totalling 27.9 GB in bin, pt, pth, safetensors.

Weights63 files · 27.9 GB
Configuration18 files · 174.5 KB
Documentation10 files · 47.4 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
checkpoint-1000/adapter_model.safetensorsWeights2.3 GB 6eef9d96f610
checkpoint-1000/optimizer.ptWeights778.4 MB d6ceebe3ce3a
checkpoint-1000/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-1000/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-1000/scaler.ptWeights1.4 KB 9aa7e5f7f336
checkpoint-1000/scheduler.ptWeights1.5 KB 8ad53cc76623
checkpoint-1000/training_args.binWeights5.7 KB 00e0cd8677bb
checkpoint-1200/adapter_model.safetensorsWeights2.3 GB 3cd2d7421339
checkpoint-1200/optimizer.ptWeights778.4 MB 8e0d24d0759a
checkpoint-1200/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-1200/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-1200/scaler.ptWeights1.4 KB 526edfc17cc7
checkpoint-1200/scheduler.ptWeights1.5 KB 9a7bdab7cc3f
checkpoint-1200/training_args.binWeights5.7 KB 00e0cd8677bb
checkpoint-1400/adapter_model.safetensorsWeights2.3 GB 26772429c8f0
checkpoint-1400/optimizer.ptWeights778.4 MB 425e1a08adcc
checkpoint-1400/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-1400/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-1400/scaler.ptWeights1.4 KB 5b8ca9a66a3e
checkpoint-1400/scheduler.ptWeights1.5 KB aa63a3279adc
checkpoint-1400/training_args.binWeights5.7 KB 00e0cd8677bb
checkpoint-1600/adapter_model.safetensorsWeights2.3 GB 986749267ec8
checkpoint-1600/optimizer.ptWeights778.4 MB ab031e45995e
checkpoint-1600/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-1600/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-1600/scaler.ptWeights1.4 KB 3c664a7891dc
checkpoint-1600/scheduler.ptWeights1.5 KB fd892d795a1a
checkpoint-1600/training_args.binWeights5.7 KB 00e0cd8677bb
checkpoint-1800/adapter_model.safetensorsWeights2.3 GB 4bd01e68a9f6
checkpoint-1800/optimizer.ptWeights778.4 MB e4173ebb4dff
checkpoint-1800/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-1800/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-1800/scaler.ptWeights1.4 KB bbb820edb9cb
checkpoint-1800/scheduler.ptWeights1.5 KB d6c5ddb7139c
checkpoint-1800/training_args.binWeights5.7 KB 00e0cd8677bb
checkpoint-200/adapter_model.safetensorsWeights2.3 GB 79a957d33c89
checkpoint-200/optimizer.ptWeights778.4 MB 675c29f25352
checkpoint-200/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-200/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-200/scaler.ptWeights1.4 KB 0e8bef6dda51
checkpoint-200/scheduler.ptWeights1.5 KB a45cc9251865
checkpoint-200/training_args.binWeights5.7 KB d6460c10ce78
checkpoint-400/adapter_model.safetensorsWeights2.3 GB 682be2c3a175
checkpoint-400/optimizer.ptWeights778.4 MB 9fec00d87e37
checkpoint-400/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-400/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-400/scaler.ptWeights1.4 KB 74d64db17f55
checkpoint-400/scheduler.ptWeights1.5 KB 34127aaa7103
checkpoint-400/training_args.binWeights5.7 KB d6460c10ce78
checkpoint-600/adapter_model.safetensorsWeights2.3 GB b7fda4667c8d
checkpoint-600/optimizer.ptWeights778.4 MB b4c657158c5c
checkpoint-600/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-600/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-600/scaler.ptWeights1.4 KB 711796bafdc9
checkpoint-600/scheduler.ptWeights1.5 KB 14f3abcef9ee
checkpoint-600/training_args.binWeights5.7 KB d6460c10ce78
checkpoint-800/adapter_model.safetensorsWeights2.3 GB 63cdf4da51f2
checkpoint-800/optimizer.ptWeights778.4 MB 1e9cd2da6e4f
checkpoint-800/rng_state_0.pthWeights14.9 KB 69d7ebf37e97
checkpoint-800/rng_state_1.pthWeights14.9 KB 145356ccf4dd
checkpoint-800/scaler.ptWeights1.4 KB 1347e41739e6
checkpoint-800/scheduler.ptWeights1.5 KB c20adce822d4
checkpoint-800/training_args.binWeights5.7 KB 00e0cd8677bb
checkpoint-1000/adapter_config.jsonConfiguration1.2 KB —
checkpoint-1000/trainer_state.jsonConfiguration18.1 KB —
checkpoint-1200/adapter_config.jsonConfiguration1.2 KB —
checkpoint-1200/trainer_state.jsonConfiguration21.6 KB —
checkpoint-1400/adapter_config.jsonConfiguration1.2 KB —
checkpoint-1400/trainer_state.jsonConfiguration25.1 KB —
checkpoint-1600/adapter_config.jsonConfiguration1.2 KB —
checkpoint-1600/trainer_state.jsonConfiguration28.6 KB —
checkpoint-1800/adapter_config.jsonConfiguration1.2 KB —
checkpoint-1800/trainer_state.jsonConfiguration32.1 KB —
checkpoint-200/adapter_config.jsonConfiguration1.2 KB —
checkpoint-200/trainer_state.jsonConfiguration4.2 KB —
checkpoint-400/adapter_config.jsonConfiguration1.2 KB —
checkpoint-400/trainer_state.jsonConfiguration7.7 KB —
checkpoint-600/adapter_config.jsonConfiguration1.2 KB —
checkpoint-600/trainer_state.jsonConfiguration11.2 KB —
checkpoint-800/adapter_config.jsonConfiguration1.2 KB —
checkpoint-800/trainer_state.jsonConfiguration14.7 KB —
README.mdDocumentation287 B —
checkpoint-1000/README.mdDocumentation5.2 KB —
checkpoint-1200/README.mdDocumentation5.2 KB —
checkpoint-1400/README.mdDocumentation5.2 KB —
checkpoint-1600/README.mdDocumentation5.2 KB —
checkpoint-1800/README.mdDocumentation5.2 KB —
checkpoint-200/README.mdDocumentation5.2 KB —
checkpoint-400/README.mdDocumentation5.2 KB —
checkpoint-600/README.mdDocumentation5.2 KB —
checkpoint-800/README.mdDocumentation5.2 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
27.9 GB
Download from Lumazini Code

Released by Lumazini Code through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published27.9 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About orpheus-3b-ptbr-lora

Can I use orpheus-3b-ptbr-lora commercially?

Yes. orpheus-3b-ptbr-lora is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text to speech

Kokoro-82M

Hexgrad

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. You can run this basic cell on Google Colab. Listen to samples. For more languages and details, see Advanced Usage. Under the hood, kokoro uses misaki, a G2P library at https://github.com/hexgrad/misaki Model SHA256 Hash: 496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4 Data: Kokoro was trained exclusively on permissive/non-copyrighted audio data and IPA…

Open weights apache-2.0
View model

Model · Text to speech

audio.cpp-gguf

Audio.cpp

This directory contains audio.cpp-native GGUF conversions of multiple speech models. These files are intended for use with audio.cpp. If you enjoy the project, please star audio.cpp on GitHub and this Hugging Face repository. For conversion details, supported layouts, direct-file loading, sidecar embedding, and the latest compatibility notes, see the audio.cpp GGUF guide: - https://github.com/0xShug0/audio.cpp/blob/main/docs/gguf.md!!! Converted and quantized packages are checked with automated metrics, but perceived quality can still differ for human listeners. Please validate the exact package, backend, and route to confirm the output is acceptable for your use case. The table lists the…

Open weights other audio.cpp
View model

Model · Text to speech

XTTS-v2

Coqui.ai

ⓍTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. There is no need for an excessive amount of training data that spans countless hours. This is the same or similar model to what powers Coqui Studio and Coqui API. - Supports 17 languages. - Voice cloning with just a 6-second audio clip. - Emotion and style transfer by cloning. - Cross-language voice cloning. - Multi-lingual speech generation. - 24khz sampling rate. - 2 new languages; Hungarian and Korean - Architectural improvements for speaker conditioning. - Enables the use of multiple speaker references and interpolation between speakers. - Stability…

Open weights other coqui
View model

Model · Text to speech

chatterbox

Resemble AI

Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages. V3 is designed for broad language coverage like V2, but with stronger stability and more expressive generation. It is the recommended multilingual model for users who want one voice cloning model that works across many languages. Try it in the Chatterbox Multilingual TTS V3 Space. Alongside V3, we are releasing the Single Language Pack: dedicated finetunes for priority languages where tighter quality control, stronger…

Open weights mit chatterbox
View model

Model · Text to speech

F5-TTS

Yushen CHEN

Download F5-TTS or E2 TTS and place under ckpts/ Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Open weights cc-by-nc-4.0 f5-tts
View model

Model · Text to speech

Kokoro-82M-v1.0-ONNX

ONNX Community

Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). First, install the kokoro-js library from NPM using: You can then generate speech as follows: Optionally, save the audio to a file: The model is resilient to quantization, enabling efficient high-quality speech synthesis at a fraction of the original model size.

Open weights apache-2.0 transformers.js
View model