-
Hi,
Okay everybody, it's a big one!
Speech in RS are recorded in propritary codec bearing the name of "MORT", MORT can be found in header of files inside "speech" file inside data.dat. Used in a …
-
Could you add a native speech to speech / audio-to-audio support with encoder (tokenizer) and decoder (back to audio waves)
I was able to implement a decoder only model, I first used audio codec to…
-
**Describe the bug**
Uploading media files via the API is returning the following error:
`Error: predictionsServices.buildChatflow - 400 Invalid file format. Supported formats: ['flac', 'm4a', 'mp…
-
I just tried to add a smart speaker which using [Linkplay A98 module](https://www.linkplay.com/modules-wifi) to Home Assistant 2024.08 it did not work well.
After adding the speaker to HA, it can sho…
-
Hey,
I am Christoph one of the co-founders of LAION.
We are working on open source Models like gpt4o and a looking for a better Audio Codec than Snac, which has some problems with very expressive…
-
-
for the 16kHz Codec model: the bitrate is 2kbps;
for the 44.1kHz Codec model: the bitrate is 6.89kbps;
for the 48kHz Codec model: the bitrate is 7.5kbps;
#1、Here is the exps/results.txt
Codec SU…
-
Here is the result for [SpeechTokenizer](https://github.com/ZhangXInFD/SpeechTokenizer).
The bit rate is 2kbps, following are the results:
**Results in exps/results.txt**
Codec SUPERB applica…
-
# 16 kHz 2kbps
## parameter size:
encoder (including quantizer) : 29MB decoder: 40MB
### exps/results.txt
Codec SUPERB application evaluation
Stage 1: Run speech emotion recognition.
Acc: 74.…
-
Hi! Nice work!
Could you share how many steps would be sufficient to train a new model? I'm trying to train a 16k FAcodec. The results reconstructed by ckpt 130,000 still sound different from the rea…