Gradio app adds support for multilingual voice fine-tunes
An update to the e2-f5-tts Gradio app enables testing custom F5-TTS fine-tunes for Spanish, Hungarian, German, Portuguese, and Greek.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
FACT rewrites context to retrieve multiple facts
Published on October 30, 2024, the paper presents FACT, an iterative context-rewriting approach for retrieving multiple facts. It examines how important information can be lost in long contexts and lead to incomplete answers.
Read articleSimpleQA evaluates model factuality
Published on October 30, 2024, SimpleQA contains 4,000 human-written factual questions, each with a single indisputable answer. An autograder labels answers correct, incorrect, or not attempted; two annotators verified the reference answers.
Read articleMaskGCT: zero-shot TTS with masked codec
A paper published on October 24, 2024 presents MaskGCT, a zero-shot text-to-speech model. The publication says it can clone a voice from five seconds of speech.
Read articleE2-F5-TTS adds a fine-tuning interface
A post dated October 21, 2024, says the E2-F5-TTS project added a Gradio app for fine-tuning the model with user-provided audio, with automatic transcription of audio clips.
Read articleWhite-hat script aims to recover funds from compromised wallets
An open-source Bash script combines Linux tools with Foundry’s cast and chisel to try to move funds before sweep bots do. Security professionals should assess the approach and its dependencies.
Read articleRAG technique tutorials in notebooks
Published on October 15, 2024, the RAG_Techniques repository collects notebooks on retrieval-augmented generation, including reranking, chunking, filtering, and Graph RAG.
Read articleLightRAG combines graphs with two-level retrieval
Published on October 13, 2024, this bookmark describes LightRAG, a RAG framework using graph-based text indexing and low- and high-level retrieval.
Read articleSpeech-to-speech toolkit for voice agents
A project published on GitHub on October 1, 2024, presents a toolkit for building voice agents with open-source models.
Read articleAirLLM describes layer-wise inference for large models
Published on September 25, 2024, the text describes loading Transformer layers from disk to avoid keeping the entire model in GPU memory.
Read articleRadar: French Parler-TTS Mini model
A September 25, 2024 post highlights the French Parler-TTS Mini model by PHBJT, hosted on a model platform. It also mentions XTTS and FishAudio and speculates about a future multilingual version.
Read articleMoshi: an open speech-to-speech model
Published on September 18, 2024, Moshi is described as a speech-to-speech model with 7.6 billion parameters, accompanied by Mimi, a streaming audio codec.
Read articleOpen-source tools for studying network filtering
A 2024 publication highlights GoodbyeDPI for Windows, ByeDPIAndroid, and zapret as open-source tools related to bypassing deep packet inspection. Engineers can evaluate them in the context of network filtering and censorship.
Read articleADAS explores search for agent design
Published on August 26, 2024, the entry describes an iterative search approach to proposing and evaluating agentic systems. The excerpt does not report the results of the tests it mentions.
Read articleFive recent RAG papers in a curated selection
Published on August 26, 2024, this briefing lists five papers on retrieval-augmented generation, covering metadata and synthetic QA, modular research frameworks, graph RAG, fact-checking, and dense retrieval with weak supervision.
Read articleVoiceCraft: speech editing and zero-shot TTS
Published on August 25, 2024, VoiceCraft is described as a neural codec language model for speech editing and zero-shot text-to-speech. The publication says it can clone or edit an unseen voice using a few seconds of reference audio.
Read articleAutoToS refines search components with tests and BFS
Published on August 23, 2024, the account describes iterative refinement of successor and goal-test functions, guided by unit-test feedback and breadth-first search (BFS) checks.
Read articleAI21 announces Jamba 1.5 Mini and Large
On August 22, 2024, AI21 Labs announced two MoE models combining Mamba and Joint Attention, with a 256K context window, ExpertInt8 quantization, JSON mode, tool use, and Transformers integration.
Read articleRadar: EfficientRAG for multi-hop questions
Published on August 17, 2024, the article presents a retrieval method that iteratively generates queries for multi-hop questions without requiring a language-model call at every iteration.
Read articleLlama 3.1 8B on an RTX 3090 under load
Published on August 16, 2024, the summary reports a benchmark of Llama 3.1 8B in fp16 on an RTX 3090: token-per-second performance was described as reasonable with more than 100 simultaneous requests.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.