CoolFace
20 results

voice-clone

Akjava /QWEN3-TTS-Voice-Clone-100-Japanese-Female-ITA-Corpus-EmotionITA-Corpus Emotion Dataset (100 Japanese Female Voices) 彼のあだ名は言い得て妙だよね 11:A lower-pitched female voice with a strong core ヒューズが飛んだ 100:A slightly quirky female voice that leaves a strong impression Overview This dataset contains 100 female voices generated with Qwen3-TTS. Format: 24kHz mono WAV Source: Link to designed voices About ITA-Corpus Emotion The text is based on the ITA-Corpus Emotion, a public domain dataset containing 100… See the full description on the dataset page: https://huggingface.co/datasets/Akjava/QWEN3-TTS-Voice-Clone-100-Japanese-Female-ITA-Corpus-Emotion.audio10K<n<100K4 likes445 downloads8mo agoHugging Facepengyichen /NaiLong-Voice-Clone 奶龙语音克隆数据集 完整项目与 Demo 效果可参见 GitHub 如果这个数据集对你有帮助,欢迎在 GitHub 上点个 Star ⭐ 支持一下! 数据集介绍 数据集按处理阶段分为以下四部分: 1. raw_audio (原始采样) 处理方式:使用 Audacity 直接对视频素材进行录音,格式为 44.1kHz, 16-bit, Stereo。 说明:包含背景音、特效及多角色对话的非结构化原片素材,是整个流水线的起点。 2. vocal_only (人声分离) 处理方式:从 raw_audio 中使用 UVR5 的 MDX-Net 模型剥离背景音乐与噪音。 说明:利用 MDX-Net 模型提取出干净的人声轨道,为后续切片提供高信噪比素材。 3. sliced_vocal (自动化切片) 处理方式:基于停顿检测、音色突变及总时长控制,将 vocal_only 自动化切分为一系列短音频。… See the full description on the dataset page: https://huggingface.co/datasets/pengyichen/NaiLong-Voice-Clone.audio10K<n<100K1 likes32 downloads5mo agoHugging Facetertrxcuvuvjvj /voiceclone-ai-apk VoiceClone AI APK Download the debug APK here. 0 likes32 downloads3d agoHugging Facebenkum /neutral-batch-voice-cloneaudio10K<n<100K1 likes28 downloads5mo agoHugging FaceMat021007 /mathieu-voice-clone31-source-atom-anticopy-retry-20260620 Voice Clone 3.1 Source-Atom Anti-Copy Retry VC31 is a system retry over the VC29 adapter: Mat021007/mathieu-voice-qwen2p5-7b-voiceclone29-dpo-vc28-split-repair-20260620 It adds source atoms and proof-time anti-copy guards because VC30 preserved source meaning better but copied too closely from held-out Mat exemplars. This is not a new accepted adapter. It is a diagnostic/progression proof. Important limitation: Source atoms are derived from held-out Mat exemplars. That is… See the full description on the dataset page: https://huggingface.co/datasets/Mat021007/mathieu-voice-clone31-source-atom-anticopy-retry-20260620.0 likes15 downloads3mo agoHugging FaceMat021007 /mathieu-voice-clone33-advice03-microfix-retry-20260620 Voice Clone 3.3 Advice 03 Micro-Fix Retry VC33 is a system retry over the VC29 adapter: Mat021007/mathieu-voice-qwen2p5-7b-voiceclone29-dpo-vc28-split-repair-20260620 It keeps the VC32 post-guard layer and changes only the advice_03 correction, because the fresh VC32 proof still produced a machine-clean but bad sentence about the helicopter flight path. This is not a new accepted adapter. It is a diagnostic/progression proof. Important limitation: Source atoms are derived from… See the full description on the dataset page: https://huggingface.co/datasets/Mat021007/mathieu-voice-clone33-advice03-microfix-retry-20260620.0 likes11 downloads3mo agoHugging Face