Instructions to use espnet/fastspeech2_conformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use espnet/fastspeech2_conformer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="espnet/fastspeech2_conformer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTextToSpectrogram tokenizer = AutoTokenizer.from_pretrained("espnet/fastspeech2_conformer") model = AutoModelForTextToSpectrogram.from_pretrained("espnet/fastspeech2_conformer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
b0dd235
1
Parent(s): 2d97a0d
Upload model
Browse files- config.json +2 -1
config.json
CHANGED
|
@@ -32,6 +32,7 @@
|
|
| 32 |
"eos_token_id": 2,
|
| 33 |
"hidden_size": 384,
|
| 34 |
"input_dim": 78,
|
|
|
|
| 35 |
"lang_embs": null,
|
| 36 |
"model_type": "fastspeech2_conformer",
|
| 37 |
"num_attention_heads": 2,
|
|
@@ -53,7 +54,7 @@
|
|
| 53 |
"stop_gradient_from_energy_predictor": false,
|
| 54 |
"stop_gradient_from_pitch_predictor": true,
|
| 55 |
"torch_dtype": "float32",
|
| 56 |
-
"transformers_version": "4.
|
| 57 |
"use_batch_norm": true,
|
| 58 |
"use_cnn_in_conformer": true,
|
| 59 |
"use_macaron_style_in_conformer": true,
|
|
|
|
| 32 |
"eos_token_id": 2,
|
| 33 |
"hidden_size": 384,
|
| 34 |
"input_dim": 78,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
"lang_embs": null,
|
| 37 |
"model_type": "fastspeech2_conformer",
|
| 38 |
"num_attention_heads": 2,
|
|
|
|
| 54 |
"stop_gradient_from_energy_predictor": false,
|
| 55 |
"stop_gradient_from_pitch_predictor": true,
|
| 56 |
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.31.0.dev0",
|
| 58 |
"use_batch_norm": true,
|
| 59 |
"use_cnn_in_conformer": true,
|
| 60 |
"use_macaron_style_in_conformer": true,
|