Wassim Seifeddine
Wassim Seifeddine
Is this implemented yet ?
Hey I'm having the same issue ```python class BiLSTMBaseline(nn.Module): def __init__(self,hidden_dim,emb_dim=300, recurrent_dropout=0.1,num_linear=1): super().__init__() self.embedding = nn.Embedding(len(TEXT.vocab),emb_dim) self.encoder = nn.LSTM(emb_dim,hidden_dim,num_linear,dropout = recurrent_dropout) self.linear_layers = [] for _ in range(num_linear - 1):...
Did you manage to make it work ?
Hello, This is from `round_bitwise` function in `quant_cpu.cpp`. Specifically `rand_prob = 1
What I'm thinking about. 1. Sockets to communicate between the server and clients 2. The sockets activate dejavu and try to recognise the stream ( Which recogniser should i use...
@julzelements Yes that's what I was thinking about. How long does this process takes? for a decent internet connection
Ahh okay, but I was looking for something more real-time. 2-3 seconds maybe. Sockets might do the trick
Hey @happy-machine. You can train your own model from this repo: https://github.com/lucidrains/spear-tts-pytorch. As far as I know, there's no pretrained models for this, or atleast I didn't find any
@shigabeev, @lucasnewman has some voice samples in the repo, You should be able to reproduce the same results. If you still need samples let me know, I might be able...