-
First of all, it is very interesting project.
Thanks for your work!
So, I'm trying to implement this project step by step on Colab(https://colab.research.google.com/drive/1fkXdwUBw9tDxofj5-us0vuOe…
-
### Feature request
When the input audio is cut off in the middle of a word, Whisper may not predict an ending timestamp. How we handle this differs between decoding using the tokenizer or using a pi…
-
https://lablab.ai/event/audiocraft-24-hours-hackathon/introspectiwavevisioneers
It's exciting to see how lablab.ai is organizing the AudioCraft 24-hours Hackathon, diving into the realm of audi…
-
is it possible to run this gghml model on raspberry pi hardware?
-
### System Info
- `transformers` version: 4.27.2
- Platform: Linux-6.2.0-76060200-generic-x86_64-with-glibc2.35
- Python version: 3.10.6
- Huggingface_hub version: 0.13.3
- PyTorch version (GPU?)…
-
### 🐛 Describe the bug
When i try to use half-precision together with the new mps backend, I get the following:
```python
>>> import torch
>>> a = torch.rand(1, device='mps')
>>> a
tensor([0.4…
-
Hello @kan-bayashi I can see gan_tts task now work with joint TTS training but wondering if you have example for specify pretrained models, switching vocoder impl and expected training time difference…
-
### Model description
paper: [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://arxiv.org/abs/2002.02562)
- Transformer-Transducer i…
-
@lucidrains Somehow i got the `MuLaN` trained with the [MusicCaps](https://www.kaggle.com/datasets/googleai/musiccaps) dataset. Now i want to check how close the `text` and `wav` embeddings are. So wh…
-
### 1. System information
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
- TensorFlow installation (pip package or built from source):
- TensorFlow library (version, if pip package or…