DeepVoice3 multi-speaker TTS en demo.ipynb fixes

[CaptainStabs]

Couldn't find the notebook on this repo so I'll just put the changes here.
On running the notebook, a FileNotFoundError is thrown due to the repo being cloned into /content/ instead of /root/

try:
  os.chdir(join(expanduser("~"), name))
except FileNotFoundError:
  os.chdir("/content/deepvoice3_pytorch")

# Use pytorch v0.3.1
!pip install -q torch==0.3.1```

[rachejazz]

Another fix with placing %cd in:

%cd ~
import os
from os.path import exists, join, expanduser

# Clone
name = "deepvoice3_pytorch"
if not exists(name):
  ! git clone https://github.com/r9y9/$name

[mdkberry]

neither of these work, getting
"ERROR: Could not find a version that satisfies the requirement torch==0.3.1 (from versions: 0.1.2, 0.1.2.post1, 0.1.2.post2, 0.4.1, 0.4.1.post2, 1.0.0, 1.0.1, 1.0.1.post2, 1.1.0, 1.2.0, 1.3.0, 1.3.1, 1.4.0, 1.5.0, 1.5.1, 1.6.0, 1.7.0, 1.7.1, 1.8.0)
ERROR: No matching distribution found for torch==0.3.1"