model_index.json

{
  "_class_name": "WanSpeechToVideoPipeline",
  "_diffusers_version": "0.36.0.dev0",
  "audio_encoder": [
    "transformers",
    "Wav2Vec2ForCTC"
  ],
  "audio_processor": [
    "transformers",
    "Wav2Vec2Processor"
  ],
  "scheduler": [
    "diffusers",
    "UniPCMultistepScheduler"
  ],
  "text_encoder": [
    "transformers",
    "UMT5EncoderModel"
  ],
  "tokenizer": [
    "transformers",
    "T5TokenizerFast"
  ],
  "transformer": [
    "diffusers",
    "WanS2VTransformer3DModel"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKLWan"
  ]
}