-
**Why**
With quite a few models available, great pricing, the ability to add your own models of fine-tunes, and a fairly simple API, NLP Cloud would be a great addition to big-AGI
**Description**
…
-
How can we objectively evaluate our model?
Some random thoughts below:
1. **Intrusive v.s. non-intrusive metrics**
In speech generation, we generally have 2 kind of metrics: intrusive and non-…
-
## Deep Learning for Text-to-Speech Synthesis, using the Merlin toolkit
This [tutorial](http://www.interspeech2017.org/program/tutorial-descriptions/) will combine the theory and practical applicat…
-
Hello, thank you very much for the new awesome fantastic wonderful media player :) 💯 🥇
Please i have request : we can download anime in Japanese from streaming sites which have 700 episodes which c…
-
Hi,
We're testing merlin_synthesis.py which reads a utts.data text file as input for speech generation. Question is, how can we insert pauses and/or silences via the utts.data file?
Thanks!
-
Hello.
I was trying to prepare microsoft speech api 5.4 bindings but failed.
Typelib generation went relatively well except few notices about unsupported parts of typelib, but the compilation failed w…
-
```python
load_dotenv()
api_key = os.getenv("GENAI_API_KEY")
if not api_key:
api_key = st.secrets["GENAI_API_KEY"]
if not api_key:
st.er…
-
Amazon changed how the intent schema and custom slots have to look like, it's one JSON object now:
[https://developer.amazon.com/docs/smapi/interaction-model-schema.html](https://developer.amazon.com…
-
### What feature?
Overview:
First create a button on Sidebar - Button Name: **Tech Resources**
When a user clicks on this button a new page should open
**In this Tech Resources Page**
Firs…
-
Hi, this is an amazing work that combines understanding and generation into one single tokenizer. Have you guys tried lower bandwidth, e.g. less than 20 or even 15 tokens per second?