From 764ace78046e78cce36b64cb3682cc5489bcf9d7 Mon Sep 17 00:00:00 2001 From: soryu Date: Thu, 29 Jan 2026 02:24:04 +0000 Subject: fix: Use correct hf command for Qwen3-TTS download (#46) * chore: fix unused import warnings in qwen3-tts module - Remove unused import 'IndexOp' in model.rs - Remove unused import 'DType' in speech_tokenizer.rs - Add #[allow(dead_code)] to codebook_dim field in RvqCodebook Co-Authored-By: Claude Opus 4.5 * feat: add voice loading and selection for TTS cloning Add voice reference audio loading so the TTS speak handler can perform voice cloning using reference WAV files from the voices/ directory. - Add voice.rs module: loads manifest.json and reference.wav for a given voice_id, decodes via symphonia, resamples to 24kHz for the TTS engine - Update speak.rs: resolve voice_id from the speak request (default "makima"), load reference audio, pass it to engine.generate() - Add voices/makima/README.md with instructions for obtaining reference audio (extraction from YouTube, recording, ffmpeg conversion) - Graceful fallback: if reference audio is missing, TTS proceeds without voice cloning using the model's default voice Co-Authored-By: Claude Opus 4.5 * feat: add inference cancellation support for TTS generation Add cooperative cancellation via Arc cancel flag that threads through TtsEngine::generate -> Qwen3Tts -> GenerationContext. The autoregressive loop and streaming decoder check the flag each iteration and break early when set. The speak WebSocket handler creates a per-session flag, passes it to generate, and sets it on Cancel/Stop/Close messages. Co-Authored-By: Claude Opus 4.5 * Add Qwen3-TTS model download to build process Fix TTS engine failure due to missing tokenizer by downloading Qwen3-TTS models during Docker build: - Download model.safetensors, config.json, tokenizer.json, and tokenizer_config.json from Qwen/Qwen3-TTS-12Hz-0.6B-Base - Download speech tokenizer from Qwen/Qwen3-TTS-Tokenizer-12Hz - Add QWEN3_TTS_DIR environment variable to Dockerfile - Script supports both env var override and default path Co-Authored-By: Claude Opus 4.5 * fix: use correct hf command for Qwen3-TTS download Co-Authored-By: Claude Opus 4.5 --------- Co-authored-by: Claude Opus 4.5 --- makima/sh/download-models.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'makima/sh') diff --git a/makima/sh/download-models.sh b/makima/sh/download-models.sh index 1aefad8..4d791af 100755 --- a/makima/sh/download-models.sh +++ b/makima/sh/download-models.sh @@ -128,7 +128,7 @@ download_qwen3_tts() { # Download base TTS model files from Qwen/Qwen3-TTS-12Hz-0.6B-Base echo "Downloading Qwen3-TTS-12Hz-0.6B-Base..." - huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base \ + hf download Qwen/Qwen3-TTS-12Hz-0.6B-Base \ model.safetensors \ config.json \ tokenizer.json \ @@ -138,7 +138,7 @@ download_qwen3_tts() { # Download speech tokenizer from Qwen/Qwen3-TTS-Tokenizer-12Hz echo "Downloading Qwen3-TTS-Tokenizer-12Hz..." local tmpdir=$(mktemp -d) - huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz \ + hf download Qwen/Qwen3-TTS-Tokenizer-12Hz \ model.safetensors \ --local-dir "$tmpdir" mv "$tmpdir/model.safetensors" "$QWEN3_TTS_DIR/speech_tokenizer.safetensors" -- cgit v1.2.3