Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
language: "
|
| 3 |
tags:
|
| 4 |
- text-to-speech
|
| 5 |
- TTS
|
|
@@ -8,7 +8,7 @@ tags:
|
|
| 8 |
- speechbrain
|
| 9 |
license: "apache-2.0"
|
| 10 |
datasets:
|
| 11 |
-
-
|
| 12 |
metrics:
|
| 13 |
- mos
|
| 14 |
---
|
|
@@ -17,7 +17,7 @@ metrics:
|
|
| 17 |
|
| 18 |
### Text-to-Speech (TTS) with Tacotron2 trained on Professional Studio Recordings
|
| 19 |
|
| 20 |
-
This repository provides all the necessary tools for Text-to-Speech (TTS) with SpeechBrain
|
| 21 |
|
| 22 |
The pre-trained model takes in input a short text and produces a spectrogram in output. One can get the final waveform by applying a vocoder (e.g., HiFIGAN) on top of the generated spectrogram.
|
| 23 |
|
|
@@ -28,8 +28,6 @@ The pre-trained model takes in input a short text and produces a spectrogram in
|
|
| 28 |
pip install speechbrain
|
| 29 |
```
|
| 30 |
|
| 31 |
-
Please notice that we encourage you to read our tutorials and learn more about
|
| 32 |
-
[SpeechBrain](https://speechbrain.github.io).
|
| 33 |
|
| 34 |
### Perform Text-to-Speech (TTS)
|
| 35 |
|
|
@@ -39,7 +37,7 @@ from speechbrain.pretrained import Tacotron2
|
|
| 39 |
from speechbrain.pretrained import HIFIGAN
|
| 40 |
|
| 41 |
# Intialize TTS (tacotron2) and Vocoder (HiFIGAN)
|
| 42 |
-
tacotron2 = Tacotron2.from_hparams(source="
|
| 43 |
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder")
|
| 44 |
|
| 45 |
# Running the TTS
|
|
|
|
| 1 |
---
|
| 2 |
+
language: "lg"
|
| 3 |
tags:
|
| 4 |
- text-to-speech
|
| 5 |
- TTS
|
|
|
|
| 8 |
- speechbrain
|
| 9 |
license: "apache-2.0"
|
| 10 |
datasets:
|
| 11 |
+
- SALT-TTS
|
| 12 |
metrics:
|
| 13 |
- mos
|
| 14 |
---
|
|
|
|
| 17 |
|
| 18 |
### Text-to-Speech (TTS) with Tacotron2 trained on Professional Studio Recordings
|
| 19 |
|
| 20 |
+
This repository provides all the necessary tools for Text-to-Speech (TTS) with SpeechBrain.
|
| 21 |
|
| 22 |
The pre-trained model takes in input a short text and produces a spectrogram in output. One can get the final waveform by applying a vocoder (e.g., HiFIGAN) on top of the generated spectrogram.
|
| 23 |
|
|
|
|
| 28 |
pip install speechbrain
|
| 29 |
```
|
| 30 |
|
|
|
|
|
|
|
| 31 |
|
| 32 |
### Perform Text-to-Speech (TTS)
|
| 33 |
|
|
|
|
| 37 |
from speechbrain.pretrained import HIFIGAN
|
| 38 |
|
| 39 |
# Intialize TTS (tacotron2) and Vocoder (HiFIGAN)
|
| 40 |
+
tacotron2 = Tacotron2.from_hparams(source="/Sunbird/sunbird-lug-tts", savedir="tmpdir_tts")
|
| 41 |
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder")
|
| 42 |
|
| 43 |
# Running the TTS
|