debpalash
fc76e79ff8
- Implement donate page and migrate API fetching to react-query hooks - Add setup wizard for batch job management and voice clip editing - Refactor setup router into package (wizard, models, download sub-modules) - Fix 9 CI test failures from setup router refactor - Fix cross-device link error in prefs.py atomic writes - Fix event loop mismatch in export test fixtures - Modernize README with architecture diagram and 13 app screenshots - Defer per-segment disk writes in dub_generate for ~6s faster dubs - Extract 45 inline styles from Launchpad, KeyboardCheatsheet, DubSegmentRow - Add playwright dev dep and screenshot capture script
124 lines
4.8 KiB
YAML
124 lines
4.8 KiB
YAML
# ── OmniVoice Studio — Model Catalog ─────────────────────────────────────
|
|
#
|
|
# This file is the source of truth for all known HuggingFace models.
|
|
# The backend loads it at startup via `load_model_catalog()`.
|
|
#
|
|
# To add a model: append an entry with the fields below.
|
|
# To remove: delete the entry. The UI will stop showing it immediately.
|
|
#
|
|
# Fields:
|
|
# repo_id (required) — HuggingFace repository ID
|
|
# label (required) — Human-readable display name
|
|
# role (required) — TTS | ASR | Diarisation
|
|
# size_gb (required) — Approximate download size in GiB
|
|
# required (optional) — true if the app needs this model to function
|
|
# platforms (optional) — restrict to specific OS+arch tags (e.g. darwin-arm64, cuda)
|
|
# note (optional) — shown in the UI as a tooltip/footnote
|
|
# ─────────────────────────────────────────────────────────────────────────
|
|
|
|
models:
|
|
# ── Required ──────────────────────────────────────────────────────────
|
|
|
|
- repo_id: "k2-fsa/OmniVoice"
|
|
label: "OmniVoice TTS (600+ languages, zero-shot)"
|
|
role: TTS
|
|
size_gb: 2.4
|
|
required: true
|
|
|
|
- repo_id: "Systran/faster-whisper-large-v3"
|
|
label: "Whisper large-v3 (faster-whisper — default, cross-platform)"
|
|
role: ASR
|
|
size_gb: 2.9
|
|
required: true
|
|
|
|
# ── Optional ASR ──────────────────────────────────────────────────────
|
|
|
|
- repo_id: "mlx-community/whisper-large-v3-mlx"
|
|
label: "Whisper large-v3 (MLX — optional mac-ARM speedup)"
|
|
role: ASR
|
|
size_gb: 3.0
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "openai/whisper-large-v3"
|
|
label: "Whisper large-v3 (PyTorch — last-resort fallback)"
|
|
role: ASR
|
|
size_gb: 3.1
|
|
platforms: [cuda]
|
|
|
|
- repo_id: "mlx-community/whisper-tiny-mlx"
|
|
label: "Whisper tiny (MLX ASR — fast fallback)"
|
|
role: ASR
|
|
size_gb: 0.08
|
|
platforms: [darwin-arm64]
|
|
|
|
# ── Diarisation ───────────────────────────────────────────────────────
|
|
|
|
- repo_id: "pyannote/speaker-diarization-3.1"
|
|
label: "pyannote speaker diarisation (multi-speaker videos)"
|
|
role: Diarisation
|
|
size_gb: 0.8
|
|
note: "Needs an HF_TOKEN with license accepted."
|
|
|
|
# ── Optional TTS ──────────────────────────────────────────────────────
|
|
|
|
- repo_id: "OpenMOSS-Team/MOSS-TTS-Nano-100M"
|
|
label: "MOSS-TTS-Nano 100M (20 langs, CPU-realtime)"
|
|
role: TTS
|
|
size_gb: 0.4
|
|
|
|
- repo_id: "KittenML/kitten-tts-mini-0.8"
|
|
label: "KittenTTS (English, 8 preset voices, CPU realtime)"
|
|
role: TTS
|
|
size_gb: 0.08
|
|
|
|
# ── mlx-audio engines (Apple Silicon only) ────────────────────────────
|
|
|
|
- repo_id: "mlx-community/Kokoro-82M-bf16"
|
|
label: "Kokoro 82M (8 langs, small, mlx-audio default)"
|
|
role: TTS
|
|
size_gb: 0.15
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "mlx-community/csm-1b-8bit"
|
|
label: "CSM 1B (voice cloning, mlx-audio)"
|
|
role: TTS
|
|
size_gb: 1.1
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "mlx-community/Qwen3-TTS-12Hz-1.7B-VoiceDesign-4bit"
|
|
label: "Qwen3-TTS 1.7B 4bit (voice design, mlx-audio)"
|
|
role: TTS
|
|
size_gb: 1.4
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "mlx-community/Dia-1.6B"
|
|
label: "Dia 1.6B (expressive, mlx-audio)"
|
|
role: TTS
|
|
size_gb: 3.2
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "mlx-community/Llama-OuteTTS-1.0-1B-4bit"
|
|
label: "Llama-OuteTTS 1.0 1B 4bit (voice clone, mlx-audio)"
|
|
role: TTS
|
|
size_gb: 0.8
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "mlx-community/Chatterbox-TTS-4bit"
|
|
label: "Chatterbox TTS 4bit (mlx-audio)"
|
|
role: TTS
|
|
size_gb: 0.5
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|
|
|
|
- repo_id: "mlx-community/MeloTTS-English-v3-MLX"
|
|
label: "MeloTTS English v3 (mlx-audio)"
|
|
role: TTS
|
|
size_gb: 0.2
|
|
note: "Apple Silicon only — via mlx-audio backend."
|
|
platforms: [darwin-arm64]
|