Links to pretrained models

DeepSpeech
#50

Contributions are welcome, I have asked for help on the french model a lot of times. I am not working anymore on that at all, so I can only work on the french model on my spare time. And my spare time is negative for months.

#51

Dear @LucieDevGirl, first of all thanks for your interest in DeepSpeech! First of all, the project certainly isn’t dead. In fact very soon there will be announced a grants programme for DeepSpeech. In terms of the different models, there has been no release since December, but a lot of people have been working on models for different languages. If you’re interested we’d be happy to discuss more about how you can participate on Mozilla’s Matrix. I haven’t been working on French because it is already a very well resourced language, but I’d be happy to help out with support etc.

1 Like
#52

How can I contribute more that giving data on common-voice ? I would be happy to contribute to a french model more efficient !

2 Likes
#53

Let’s talk on Matrix! :slight_smile:

#54

I think the problem is the memory because when the audio is short I can load the file

#55

if i want to use your spanish model, I only need to put the path of the model in checkpoint_file right? but I have a question in the code testing_tflite.py the acoustic model is in enlgish, do i need an acoustic model for spanish? or I only need the language model in spanish? because I’ve understood that the acoustic model is like the pronunciation and the language model is the grammar but the pronunciation in spanish is different that english

#56

Yes, you need both models

#57

Has anybody found a Japanese language model?

Maybe it can be trained on this 2000 hour corpus: https://github.com/laboroai/LaboroTVSpeech

The Mozilla Common Voice corpus for Japanese is very small (26 hours, 639 MB).

#58

Hello @ftyers is this possible to update your link ? Im interrested to test your wolof model if possible :wink:

#59

Did anybody train the acoustic model on 8khz audio?
Would it be possible to share it for testing?

#60

I trained an Esperanto model with 720 hours and a WER around 20-30% using Coqui AI which is backwards compatible to Deepspeech. I document the work in this Repo: https://github.com/parolteknologio/stt-esperanto

You can also find some experimental Scorers and Colab Notebooks there, including a Colab Notebook to create subtitles in Esperanto using AutoSub. We also have a small website: https://parolteknologio.github.io/

Edit: There is also an Esperanto Vosk Model that can be used in many tools such as Kdenlive to create subtitles: https://alphacephei.com/vosk/models
It has the impressive WER of 8.28% and is very usable.

2 Likes
#61

Here it is: https://models.omnilingo.cc/wo/
Sorry for the delay, I didn’t see the post until now!

#62

Hey,
I see your message just now.
Your link seems oudated ?

Capture d’écran de 2022-01-04 15-19-41
Capture d’écran de 2022-01-04 15-19-411619×189 10 KB

#63

Hey there, you can try: https://itml.cl.indiana.edu/models/wo/ :slight_smile:

1 Like
#64

Your models are awesome, i have only one question, i would like to improve the spanish model, I mean when i run the model i takes 20 seconds to convert speech to text but i would like to improve that time almost to 10 seconds to convert speech to text, could you give any advice? maybe train again the model in C++ instead python to improve the speed of the model? (the accuracy is good i want only improve the speed)

#65

Hi, I am trying to access Swahili pre-trained model at https://tepozcatl.omnilingo.cc/sw but link is down. Can you please update/share the new link to download the model?

Thanks

1 Like