model_index.json

{
  "_class_name": "AudioLDMPipeline",
  "_diffusers_version": "0.13.0.dev0",
  "scheduler": [
    "diffusers",
    "DDIMScheduler"
  ],
  "text_encoder": [
    "transformers",
    "ClapTextModelWithProjection"
  ],
  "tokenizer": [
    "transformers",
    "RobertaTokenizerFast"
  ],
  "unet": [
    "diffusers",
    "UNet2DModel"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKL"
  ],
  "vocoder": [
    "transformers",
    "SpeechT5HifiGan"
  ]
}