-
### Description
we are going to get an estimation of time and cost for training the whisper model. the whisper model is previously trained on 500 hours of training data but now we have 1500 hours tra…
-
### Description
we are currently using 0.5 percent of the total training samples for the test. this is not a well generalization of test set to evaluate the model. we will be creating a test set of 1…
-
When I tested the new dataset, which has large nunber of siginicands I met:
alp/benchmarks/bench_compression_ratio/bench_alp_compression_ratio.cpp(293): error: Expected equality of these values:
…
-
### Description
We need to train stt-wav2vec2 model on the new datasets that we have gained also because of the new departments data introduced.
### Completion Criteria
Stt wav2vec2 model with better…
-
Hi there,
I wanted to express my appreciation for the intriguing and innovative STT method you've developed. It's truly fascinating, and I've been excited to explore the example code you've provide…
-
# RFW0115: Evaluate model results in more detail for STT_NS using speaker ID
## Summary
Evaluate model performance on different categories within STT_NS using the segment ID and the speaker metad…
-
### Description
The goal is to develop a Tibetan text-to-speech (TTS) model that can convert Tibetan text into Tibetan speech. This project involves training a TTS model using filtered good audio qual…
-
[Here](https://console.groq.com/docs/speech-text) are the docs for the new Whisper models available in Groq Cloud. I'd like to replace my Deepgram STT provider with the Groq transcription service. It …
-
**is there an implementation for audio recognizing**
Example : i want to pass 1 sec of audio to a model and output the prediction
-
# RFW0113: Test Distil Whisper Model
## Summary
Train Distil Whisper Model and measure performance against benchmark dataset.
## Key Concepts
Distil Whisper: A Whisper Model with reduced laye…