Spaces:
Running
Running
Update README
Browse files
README.md
CHANGED
@@ -34,7 +34,7 @@ ClipScript is a powerful application that transforms any video or audio content
|
|
34 |
|
35 |
This application has been submitted to the **Agent Demo Track**. It showcases an "AI agent" that acts as an expert blog writer and editor, taking a high-level goal (transforming a transcript) and executing a series of steps to achieve it.
|
36 |
|
37 |
-
##
|
38 |
|
39 |
### Speech-to-Text: NVIDIA Parakeet TDT 0.6B V2
|
40 |
|
@@ -42,6 +42,9 @@ The transcription engine is powered by `nvidia/parakeet-tdt-0.6b-v2`. This model
|
|
42 |
|
43 |
For a deep dive into the model's architecture and performance, check out the [official model card](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) and the [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard).
|
44 |
|
|
|
|
|
|
|
45 |
### Content Generation: AI Writing Agent
|
46 |
|
47 |
An AI writing agent, accessed via OpenRouter, converts the raw transcript into a polished, structured blog post, ready for publishing.
|
|
|
34 |
|
35 |
This application has been submitted to the **Agent Demo Track**. It showcases an "AI agent" that acts as an expert blog writer and editor, taking a high-level goal (transforming a transcript) and executing a series of steps to achieve it.
|
36 |
|
37 |
+
## Core Technology
|
38 |
|
39 |
### Speech-to-Text: NVIDIA Parakeet TDT 0.6B V2
|
40 |
|
|
|
42 |
|
43 |
For a deep dive into the model's architecture and performance, check out the [official model card](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) and the [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard).
|
44 |
|
45 |
+
|
46 |
+
For audio longer than 30 minutes, the SST model automatically segments content into optimal chunks and processes them in parallel, enabling fast transcription of hours-long content while maintaining accuracy and context.
|
47 |
+
|
48 |
### Content Generation: AI Writing Agent
|
49 |
|
50 |
An AI writing agent, accessed via OpenRouter, converts the raw transcript into a polished, structured blog post, ready for publishing.
|