Mirrors
/
diffusers
mirror of https://github.com/ShivamShrirao/diffusers.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update speech example

This commit is contained in:
Suraj Patil 2022-06-16 18:33:49 +02:00 committed by GitHub
parent 7cabc0cddc
commit 20c722c601
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@ -232,35 +232,26 @@ image_pil = PIL.Image.fromarray(image_processed[0])
image_pil.save("test.png") image_pil.save("test.png")
``` ```
#### **Text to speech with BDDM** #### **Text to speech with GradTTS and BDDM**
_Follow the instructions [here](https://pytorch.org/hub/nvidia_deeplearningexamples_tacotron2/) to load tacotron2 model._
```python ```python
import torch import torch
from diffusers import BDDM, DiffusionPipeline from diffusers import BDDM, GradTTS
torch_device = "cuda" torch_device = "cuda"
# load the BDDM pipeline # load grad tts and bddm pipelines
bddm = DiffusionPipeline.from_pretrained("fusing/diffwave-vocoder-ljspeech") grad_tts = GradTTS.from_pretrained("fusing/grad-tts-libri-tts")
bddm = BDDM.from_pretrained("fusing/diffwave-vocoder-ljspeech")
# load tacotron2 to get the mel spectograms
tacotron2 = torch.hub.load('NVIDIA/DeepLearningExamples:torchhub', 'nvidia_tacotron2', model_math='fp16')
tacotron2 = tacotron2.to(torch_device).eval()
text = "Hello world, I missed you so much." text = "Hello world, I missed you so much."
utils = torch.hub.load('NVIDIA/DeepLearningExamples:torchhub', 'nvidia_tts_utils')
sequences, lengths = utils.prepare_input_sequence([text])
# generate mel spectograms using text # generate mel spectograms using text
with torch.no_grad(): mel_spec = grad_tts(text)
mel_spec, _, _ = tacotron2.infer(sequences, lengths)
# generate the speech by passing mel spectograms to BDDM pipeline # generate the speech by passing mel spectograms to BDDM pipeline
generator = torch.manual_seed(0) generator = torch.manual_seed(42)
audio = bddm(mel_spec, generator, torch_device) audio = bddm(mel_spec, generator)
# save generated audio # save generated audio
from scipy.io.wavfile import write as wavwrite from scipy.io.wavfile import write as wavwrite