testadmin
/
Parakeet
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix sample file name

This commit is contained in:
liuyibing01 2020-03-07 14:21:35 +00:00 committed by lifuchen
parent f7ec215b9a
commit e82115bc8a
2 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/waveflow/README.md
View File

@ -4,7 +4,7 @@ PaddlePaddle dynamic graph implementation of [WaveFlow: A Compact Flow-based Mod
- WaveFlow can synthesize 22.05 kHz high-fidelity speech around 40x faster than real-time on a Nvidia V100 GPU without engineered inference kernels, which is faster than [WaveGlow] (https://github.com/NVIDIA/waveglow) and serveral orders of magnitude faster than WaveNet.
- WaveFlow is a small-footprint flow-based model for raw audio. It has only 5.9M parameters, which is 15x smalller than WaveGlow (87.9M) and comparable to WaveNet (4.6M).
- WaveFlow is directly trained with maximum likelihood without probability density distillation and auxiliary losses as used in Parallel WaveNet and ClariNet, which simplifies the training pipeline and reduces the cost of development.
- WaveFlow is directly trained with maximum likelihood without probability density distillation and auxiliary losses as used in Parallel WaveNet and ClariNet, which simplifies the training pipeline and reduces the cost of development.
## Project Structure
```text
@ -99,7 +99,7 @@ python -u synthesis.py \
--sigma=1.0
```
In this example, `--output` specifies where to save the synthesized audios and `--sample` specifies which sample in the valid dataset (a split from the whole LJSpeech dataset, by default contains the first 16 audio samples) to synthesize based on the mel-spectrograms computed from the ground truth sample audio, e.g., `--sample=0` means to synthesize the first audio in the valid dataset.
In this example, `--output` specifies where to save the synthesized audios and `--sample` (<16) specifies which sample in the valid dataset (a split from the whole LJSpeech dataset, by default contains the first 16 audio samples) to synthesize based on the mel-spectrograms computed from the ground truth sample audio, e.g., `--sample=0` means to synthesize the first audio in the valid dataset.
### Benchmarking

9
parakeet/models/waveflow/waveflow.py
View File

@ -179,10 +179,13 @@ class WaveFlow():
mels_list = [mels for _, mels in self.validloader()]
if sample is not None:
mels_list = [mels_list[sample]]
else:
sample = 0
for sample, mel in enumerate(mels_list):
filename = "{}/valid_{}.wav".format(output, sample)
print("Synthesize sample {}, save as {}".format(sample, filename))
for idx, mel in enumerate(mels_list):
abs_idx = sample + idx
filename = "{}/valid_{}.wav".format(output, abs_idx)
print("Synthesize sample {}, save as {}".format(abs_idx, filename))
start_time = time.time()
audio = self.waveflow.synthesize(mel, sigma=self.config.sigma)