전체 검색

AI 모델 2119

• Llama-OuteTTS-1.0-1B↗

  unsloth

  > [!IMPORTANT] > **Important Sampling Considerations** > > When using OuteTTS version 1.0, it is crucial to use the settings specified in the Sampling Configuration section. > > The **repetition penalty implementation** is particularly important - this model requires penalization applied to a **64-token recent window**, > rather than across the entire context window. Penalizing the entire context will cause the model to produce **broken or low-quality output**. > > Currently, **llama.cpp** delivers the most reliable and consistent output quality by default. > Both **llama.cpp** and **EXL2** support this windowed sampling approach, while **Transformers** doesn't. > > To address this limitation, I've implemented a **windowed repetition penalty** for the **Hugging Face Transformers** backend in the **OuteTTS** library, > which significantly improves output quality and resolves sampling issues, providing comparable results to llama.cpp. This update brings significant improvements in speech synthesis and voice cloning—delivering a more powerful, accurate, and user-friendly experience in a compact size. The model is designed to be used with a speaker reference. Without one, it generates random vocal characteristics, often leading to lower-quality outputs. The model inherits the referenced speaker's emotion, style, and accent. When transcribing to other languages with the same speaker, you may observe the model retaining the original accent.

• colqwen2.5-v0.2↗

  vidore

  ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a Qwen2.5-VL-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali. Maximal resolution is set so that 768 image patches are created at most. Experiments show clear improvements with larger amounts of image patches, at the cost of memory requirements. Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both *ViDoRe* and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.

• rudialogpt3_medium_based_on_gpt2_2ch↗

  BlackSamorez

• mms-tts-tel↗

  facebook

  This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. VITS (**V**ariational **I**nference with adversarial learning for end-to-end **T**ext-to-**S**peech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text.

• wav2vec2-large-lv60↗

  facebook

  The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. **Abstract** We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.

• MiniMax-H3-Turbo-Lora-ComfyUI↗

  drbaph

  This repository contains MiniMax-H3 Turbo and few-step LoRAs converted and optimized for ComfyUI. These LoRAs accelerate MiniMax-H3 video and synchronized-audio generation by reducing the required number of sampling steps. - Video-Rebirth/hyperflow — GitHub - videorebirth/hyperflow — Hugging Face

• FLUX-3-KLEIN-MODELS↗

  KoalaNation

  > **Ungated mirror of black-forest-labs/flux-3-image-klein-comfy.** > All credit to Black Forest Labs — this is not an official Black Forest Labs > release and is not endorsed by them. The weights are redistributed under the > FLUX Kommunity License, included here as `LICENSE.md` together > with `NOTICE.md`; any rights to use them are granted directly by > Black Forest Labs under that licence. > > **What this mirror carries** — the int8 / w4a8 builds the ComfyUI templates and > the SAUS apps use: > > | path | size | what it is | > | --- | --- | --- | > | `diffusion_models/flux3_image_klein_base_int8_convrot.safetensors` | 5.81 GB | Klein Base, undistilled — 50 steps, guidance 3.5 | > | `diffusion_models/flux3_image_klein_sd_int8_convrot.safetensors` | 5.83 GB | Klein distilled — 16 steps, no guidance | > | `text_encoders/qwen3vl_4b_int8_convrot.safetensors` | 4.86 GB | Qwen3-VL-4B-Instruct text encoder | > | `text_encoders/qwen3.5_9b_flux3_prompt_upsampler_w4a8.safetensors` | 6.72 GB | prompt upsampler | > | `vae/flux2-vae.safetensors` | 336 MB | image autoencoder | > > **Installing into ComfyUI:** copy (or symlink) `diffusion_models/` and > `text_encoders/` into `ComfyUI/models/`, and `vae/flux2-vae.safetensors` into > `ComfyUI/models/vae/`. The sub-folder layout above deliberately matches the > upstream repository, so a plain directory copy is enough. FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder. The 5.6B parameter label refers to the image transformer; the text encoder is separate.

• FrogNano-4B-2609-GGUF↗

  NANI-Nithin

  This repo contains llama.cpp GGUF conversions of **microsoft/FrogNano-4B-2609** — Microsoft Corporation's compact repository-level coding agent (released 22-SEP-2026). All 29 standard quant types are here, each cut from the BF16 checkpoint with an importance matrix computed on those same BF16 weights, plus the BF16 file itself and the vision-tower export, quantized 2026-10-04. These files are llama.cpp GGUF. They are **not** loaded by vLLM, SGLang or Transformers the way the source repo's safetensors are — use `llama-cli`, `llama-server`, or another GGUF runtime. From Microsoft's model card: FrogNano is a repository-level coding agent derived from **Qwen/Qwen3.5-4B**, post-trained exclusively with reinforcement learning on ~1,500 synthetic software-engineering tasks that were generated, validated, and calibrated against the evolving policy using TaskPilot. It operates through the lightweight five-tool **Leaf** harness (file read/write/edit, glob-based search, shell execution) inside an isolated repository sandbox. A distinctive choice: the agent post-training used **no stronger-model solution trajectories, actions, reasoning traces, or patch targets** — the model learned from its own policy's trajectories, rewarded by executable test results.

• test-gguf-sample↗

  Isotr0py

• sam-vit-tiny-random-ov↗

  katuni4ka