{ "bf16": { "description": "all linears bf16 (Breeze-TTS-2-bf16.safetensors)", "load_s": 7.6, "avg_rtf": 5.681, "max_peak_vram_gib": 7.51, "prompts": { "design_en": { "audio_s": 4.16, "gen_s": 24.1, "rtf": 5.797, "peak_vram_gib": 7.32, "logmel_l1_vs_bf16": 0.0, "wer": 0.0, "whisper": "It is good to hear your voice again after all this time." }, "design_zh": { "audio_s": 2.8, "gen_s": 14.9, "rtf": 5.324, "peak_vram_gib": 7.25, "logmel_l1_vs_bf16": 0.0, "wer": 0.0, "whisper": "欢迎来到今晚的故事时间让我们一起开始吧" }, "clone_en": { "audio_s": 6.24, "gen_s": 37.0, "rtf": 5.922, "peak_vram_gib": 7.51, "logmel_l1_vs_bf16": 0.0, "wer": 0.1667, "whisper": "This is a clone test of the Breeze TTS2 Comfy UI node pack. Now running with quantized weights." }, "direction_en": { "audio_s": 4.8, "gen_s": 27.3, "rtf": 5.68, "peak_vram_gib": 7.42, "logmel_l1_vs_bf16": 0.0, "wer": 0.0, "whisper": "We need to discuss what happened last night." } } }, "int8-convrot": { "description": "all 462 transformer linears int8 convrot (Breeze-TTS-2-int8-convrot.safetensors)", "load_s": 9.6, "avg_rtf": 9.08, "max_peak_vram_gib": 5.21, "prompts": { "design_en": { "audio_s": 4.72, "gen_s": 36.7, "rtf": 7.778, "peak_vram_gib": 5.06, "logmel_l1_vs_bf16": 1.796, "wer": 0.0833, "whisper": "Ah, it is good to hear your voice again, after all this time." }, "design_zh": { "audio_s": 4.24, "gen_s": 41.0, "rtf": 9.664, "peak_vram_gib": 5.04, "logmel_l1_vs_bf16": 3.4857, "wer": 0.0, "whisper": "欢迎来到今晚的故事时间让我们一起开始吧" }, "clone_en": { "audio_s": 6.24, "gen_s": 57.8, "rtf": 9.262, "peak_vram_gib": 5.21, "logmel_l1_vs_bf16": 1.3277, "wer": 0.2222, "whisper": "This is a clone test of the Breeze TTS2 Comfy UI node pack, now running with Quantite weights." }, "direction_en": { "audio_s": 3.68, "gen_s": 35.4, "rtf": 9.617, "peak_vram_gib": 5.07, "logmel_l1_vs_bf16": 2.1019, "wer": 0.0, "whisper": "We need to discuss what happened last night." } } }, "int8-hybrid": { "description": "backbone+text_encoder int8 convrot, depth decoder bf16 (Breeze-TTS-2-int8-hybrid.safetensors)", "load_s": 9.2, "avg_rtf": 5.642, "max_peak_vram_gib": 5.53, "prompts": { "design_en": { "audio_s": 3.52, "gen_s": 18.8, "rtf": 5.338, "peak_vram_gib": 5.3, "logmel_l1_vs_bf16": 1.634, "wer": 0.0, "whisper": "It is good to hear your voice again after all this time." }, "design_zh": { "audio_s": 4.16, "gen_s": 22.6, "rtf": 5.421, "peak_vram_gib": 5.34, "logmel_l1_vs_bf16": 3.5299, "wer": 0.0, "whisper": "欢迎来到今晚的故事时间让我们一起开始吧" }, "clone_en": { "audio_s": 6.32, "gen_s": 33.5, "rtf": 5.304, "peak_vram_gib": 5.53, "logmel_l1_vs_bf16": 1.0783, "wer": 0.2222, "whisper": "This is a clone test of the Breeze TTS2 Comfy UI node pack. Now running with quantize weights." }, "direction_en": { "audio_s": 3.84, "gen_s": 25.0, "rtf": 6.506, "peak_vram_gib": 5.38, "logmel_l1_vs_bf16": 1.9786, "wer": 0.0, "whisper": "We need to discuss what happened last night." } } }, "int8-te": { "description": "text_encoder int8 convrot only (Breeze-TTS-2-int8-text-encoder.safetensors)", "load_s": 8.4, "avg_rtf": 5.342, "max_peak_vram_gib": 6.82, "prompts": { "design_en": { "audio_s": 4.24, "gen_s": 25.1, "rtf": 5.928, "peak_vram_gib": 6.66, "logmel_l1_vs_bf16": 1.1453, "wer": 0.0, "whisper": "It is good to hear your voice again after all this time." }, "design_zh": { "audio_s": 3.44, "gen_s": 17.5, "rtf": 5.097, "peak_vram_gib": 6.61, "logmel_l1_vs_bf16": 2.3411, "wer": 0.0, "whisper": "欢迎来到今晚的故事时间,让我们一起开始吧。" }, "clone_en": { "audio_s": 6.08, "gen_s": 32.1, "rtf": 5.275, "peak_vram_gib": 6.82, "logmel_l1_vs_bf16": 1.1573, "wer": 0.2222, "whisper": "This is a clone test of the Breeze TTS2 Comfy UI node pack. Now running with quantize weights." }, "direction_en": { "audio_s": 4.48, "gen_s": 22.7, "rtf": 5.068, "peak_vram_gib": 6.73, "logmel_l1_vs_bf16": 2.6358, "wer": 0.0, "whisper": "We need to discuss what happened last night." } } } }