Spaces:
Sleeping
Sleeping
| asr_models: | |
| - id: openai/whisper-large-v3-turbo | |
| name: Whisper large-v3-turbo | |
| - id: openai/whisper-large-v3 | |
| name: Whisper large-v3 | |
| - id: openai/whisper-medium | |
| name: Whisper medium | |
| - id: openai/whisper-small | |
| name: Whisper small | |
| - id: sanchit-gandhi/whisper-small-dv | |
| name: Whisper small-dv | |
| - id: facebook/wav2vec2-base-960h | |
| name: Wav2Vec2-Base-960h | |
| llm_models: | |
| - id: google/gemma-2-2b | |
| name: Gemma 2 2B | |
| - id: MiniMaxAI/MiniMax-M1-80k | |
| name: MiniMax M1 80k | |
| - id: meta-llama/Llama-3.2-3B-Instruct | |
| name: Llama 3.2 3B Instruct | |
| svs_models: | |
| - id: mandarin-espnet/mixdata_svs_visinger2_spkemb_lang_pretrained | |
| name: Visinger2 (Bilingual)-zh | |
| model_path: espnet/mixdata_svs_visinger2_spkemb_lang_pretrained | |
| lang: mandarin | |
| voices: | |
| voice1: resource/singer/singer_embedding_ace-2.npy | |
| voice2: resource/singer/singer_embedding_ace-8.npy | |
| voice3: resource/singer/singer_embedding_itako.npy | |
| voice4: resource/singer/singer_embedding_kising_orange.npy | |
| voice5: resource/singer/singer_embedding_m4singer_Alto-4.npy | |
| - id: japanese-espnet/mixdata_svs_visinger2_spkemb_lang_pretrained | |
| name: Visinger2 (Bilingual)-jp | |
| model_path: espnet/mixdata_svs_visinger2_spkemb_lang_pretrained | |
| lang: japanese | |
| voices: | |
| voice1: resource/singer/singer_embedding_ace-2.npy | |
| voice2: resource/singer/singer_embedding_ace-8.npy | |
| voice3: resource/singer/singer_embedding_itako.npy | |
| voice4: resource/singer/singer_embedding_kising_orange.npy | |
| voice5: resource/singer/singer_embedding_m4singer_Alto-4.npy | |
| - id: mandarin-espnet/aceopencpop_svs_visinger2_40singer_pretrain | |
| name: Visinger2 (Chinese) | |
| model_path: espnet/aceopencpop_svs_visinger2_40singer_pretrain | |
| lang: mandarin | |
| voices: | |
| voice1: 5 | |
| voice2: 8 | |
| voice3: 12 | |
| voice4: 15 | |
| voice5: 29 | |
| melody_sources: | |
| - id: gen-random-none | |
| name: Random Generation | |
| desc: "Melody is generated without any structure or reference." | |
| - id: sample-note-kising | |
| name: Sampled Melody (KiSing) | |
| desc: "Melody is retrieved from KiSing dataset." | |
| - id: sample-note-touhou | |
| name: Sampled Melody (Touhou) | |
| desc: "Melody is retrieved from Touhou dataset." | |
| - id: sample-lyric-kising | |
| name: Sampled Melody with Lyrics (Kising) | |
| desc: "Melody with aligned lyrics are sampled from Kising dataset." | |