Mirror model_index.json from cvssp/audioldm2@c8e7e189
Browse files
encoders/cvssp/audioldm2/model_index.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AudioLDM2Pipeline",
|
| 3 |
+
"_diffusers_version": "0.20.0.dev0",
|
| 4 |
+
"feature_extractor": [
|
| 5 |
+
"transformers",
|
| 6 |
+
"ClapFeatureExtractor"
|
| 7 |
+
],
|
| 8 |
+
"language_model": [
|
| 9 |
+
"transformers",
|
| 10 |
+
"GPT2Model"
|
| 11 |
+
],
|
| 12 |
+
"projection_model": [
|
| 13 |
+
"audioldm2",
|
| 14 |
+
"AudioLDM2ProjectionModel"
|
| 15 |
+
],
|
| 16 |
+
"scheduler": [
|
| 17 |
+
"diffusers",
|
| 18 |
+
"DDIMScheduler"
|
| 19 |
+
],
|
| 20 |
+
"text_encoder": [
|
| 21 |
+
"transformers",
|
| 22 |
+
"ClapModel"
|
| 23 |
+
],
|
| 24 |
+
"text_encoder_2": [
|
| 25 |
+
"transformers",
|
| 26 |
+
"T5EncoderModel"
|
| 27 |
+
],
|
| 28 |
+
"tokenizer": [
|
| 29 |
+
"transformers",
|
| 30 |
+
"RobertaTokenizerFast"
|
| 31 |
+
],
|
| 32 |
+
"tokenizer_2": [
|
| 33 |
+
"transformers",
|
| 34 |
+
"T5TokenizerFast"
|
| 35 |
+
],
|
| 36 |
+
"unet": [
|
| 37 |
+
"audioldm2",
|
| 38 |
+
"AudioLDM2UNet2DConditionModel"
|
| 39 |
+
],
|
| 40 |
+
"vae": [
|
| 41 |
+
"diffusers",
|
| 42 |
+
"AutoencoderKL"
|
| 43 |
+
],
|
| 44 |
+
"vocoder": [
|
| 45 |
+
"transformers",
|
| 46 |
+
"SpeechT5HifiGan"
|
| 47 |
+
]
|
| 48 |
+
}
|