Skip to content
This repository has been archived by the owner on Feb 5, 2024. It is now read-only.

Commit

Permalink
Add female voices (#4)
Browse files Browse the repository at this point in the history
* add nancy voice

* add ljspeech voice

* docker instructions

authored-by: jarbasai <jarbasai@mailfence.com>
  • Loading branch information
JarbasAl authored Feb 28, 2022
1 parent c5e5473 commit 5dc347c
Show file tree
Hide file tree
Showing 3 changed files with 40 additions and 1 deletion.
15 changes: 15 additions & 0 deletions ljspeech.Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
FROM tensorflow/tensorflow:1.8.0-py3
RUN apt-get update && apt-get install -y python3 python3-pip git llvm-8
RUN ln -s /usr/bin/llvm-config-8 /usr/bin/llvm-config

RUN git clone https://github.com/keithito/tacotron /root/tacotron
WORKDIR /root/tacotron
RUN pip3 install -r requirements.txt

RUN mkdir /root/tacotron_models
RUN curl https://data.keithito.com/data/speech/tacotron-20180906.tar.gz -k --output /root/tacotron_models/tacotron-20180906.tar.gz
WORKDIR /root/tacotron_models
RUN tar x --file /root/tacotron_models/tacotron-20180906.tar.gz
WORKDIR /root/tacotron

CMD python3 /root/tacotron/demo_server.py --checkpoint /root/tacotron_models/tacotron-20180906/model.ckpt
12 changes: 12 additions & 0 deletions nancy.Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
FROM tensorflow/tensorflow:1.8.0-py3
RUN apt-get update && apt-get install -y python3 python3-pip git llvm-8
RUN ln -s /usr/bin/llvm-config-8 /usr/bin/llvm-config

RUN git clone https://github.com/keithito/tacotron /root/tacotron
WORKDIR /root/tacotron
RUN git reset --hard 8edcd55b3f08f0492340e8b3ee60a693138f5473
RUN pip3 install -r requirements.txt

RUN git clone https://github.com/ArkaneCow/tacotron-models /root/tacotron_models

CMD python3 /root/tacotron/demo_server.py --checkpoint /root/tacotron_models/mxgray_nancy/model.ckpt-250000
14 changes: 13 additions & 1 deletion readme.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,19 @@ OVOS TTS plugin for [Mimic2](https://github.com/MycroftAI/mimic2)

```json
"tts": {
"module": "ovos-tts-plugin-mimic2"
"module": "ovos-tts-plugin-mimic2",
"ovos-tts-plugin-mimic2": {
"url": "https://mimic-api.mycroft.ai/synthesize"
}
}

```

### Voices

Dockerfiles are provided for Nancy corpus trained by Mxgray and LJSpeech trained by Keithito
- `docker build -f nancy.Dockerfile -t mimic2-nancy`
- `docker build -f ljspeech.Dockerfile -t mimic2-ljspeech`

run the container and set url in config `http://0.0.0.0:9000/synthesize`
- `docker run --rm -p 9000:9000 mimic2-nancy`

0 comments on commit 5dc347c

Please sign in to comment.