changelog.md

neuTalk Change log (includes neuTalk + speakers)

---

05/17/22

neuTalk v0.6a

• Initial recorded version.
• Includes basic features like TalkNet wav transfer, basic voice parameter controls with WORLD, support for neuTalk-specific speaker library format (.ntk, .ntk_cfg, .ntkpkg)
• English and Japanese synthesis with TalkNet/hifi-gan and tacotron2/hifi-gan respectively. (hifi-gan models are the same format/training script)
• Multiple Voice Models under a single Speaker with 'sub-model' selection (only supports a single language)

Tiger v0.5

• Standard v1.1β | ~1h15m data
• Alpha v1.0 | ~1h42m data
• Mellow v0.8β | ~16m data
• Sing (Experimental) v1.0

Tiger (Japanese) v1.0β

• ~23m data

Glim v1.1

• Standard v1.1β | ~1h30m data

neuTalk Universal Warm-Start Model (English) v0.1

• ~26h data from 4 speakers (LJ-Speech, Tiger (Standard), Glim, another random male speaker)

neuTalk Universal Warm-Start Model (Japanese) v1.0

• ~3h data from many speakers (Mozilla Common Voice Japanese)