vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

tts : add OuteTTS support (#10784)

Browse source 
* server : add "tokens" output

ggml-ci

* server : output embeddings for all tokens when pooling = none

ggml-ci

* server : be explicit about the pooling type in the tests

ggml-ci

* server : do not normalize embeddings when there is no pooling

ggml-ci

* llama : add OuteTTS support (wip)

* wip

* extract features

* first conv

* group norm

* resnet conv

* resnet

* attn

* pos net

* layer norm

* convnext

* head

* hann window

* fix n_embd + remove llama.cpp hacks

* compute hann window

* fft

* spectrum processing

* clean-up

* tts : receive input text and generate codes

* clip : fix new conv name

* tts : minor fix

* tts : add header + minor fixes

ggml-ci

* tts : add matchematical constant

ggml-ci

* tts : fix sampling + cut initial noise

* tts : fixes

* tts : update default samplers

ggml-ci

* tts : text pre-processing

* tts : outetts-voc -> wavtokenizer-dec

* tts : remove hardcoded constants

ggml-ci

* tts : fix tensor shapes

* llama : refactor wavtokenizer tensors

ggml-ci

* cont

ggml-ci

* cont [no ci]

* llama : update WavTokenizer to non-causal attn

* llama : handle no-vocab detokenization

* tts : add Python example for OuteTTS (wip)

* tts : extend python example to generate spectrogram

ggml-ci

* server : fix rebase artifacts

* tts : enable "return_tokens" in Python example

ggml-ci

* tts : minor fixes

* common : support HF download for vocoder
This commit is contained in:
Georgi Gerganov 2024-12-18 19:27:21 +02:00 • committed by GitHub
parent 7bbb5acf12
commit 0bf2d10c55
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 2509 additions and 532 deletions
Download patch file Download diff file Expand all files Collapse all files

41
ggml/include/ggml.h
View file

@ -1564,17 +1564,6 @@ extern "C" {
int d1, // dilation dimension 1
bool is_2D);
GGML_API struct ggml_tensor * ggml_conv_depthwise_2d(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel
struct ggml_tensor * b, // data
int s0, // stride dimension 0
int s1, // stride dimension 1
int p0, // padding dimension 0
int p1, // padding dimension 1
int d0, // dilation dimension 0
int d1); // dilation dimension 1
GGML_API struct ggml_tensor * ggml_conv_1d(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel
@ -1592,6 +1581,23 @@ extern "C" {
int s, // stride
int d); // dilation
// depthwise
// TODO: this is very likely wrong for some cases! - needs more testing
GGML_API struct ggml_tensor * ggml_conv_1d_dw(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel
struct ggml_tensor * b, // data
int s0, // stride
int p0, // padding
int d0); // dilation
GGML_API struct ggml_tensor * ggml_conv_1d_dw_ph(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel
struct ggml_tensor * b, // data
int s0, // stride
int d0); // dilation
GGML_API struct ggml_tensor * ggml_conv_transpose_1d(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel
@ -1611,7 +1617,6 @@ extern "C" {
int d0, // dilation dimension 0
int d1); // dilation dimension 1
// kernel size is a->ne[0] x a->ne[1]
// stride is equal to kernel size
// padding is zero
@ -1638,6 +1643,18 @@ extern "C" {
struct ggml_tensor * a,
struct ggml_tensor * b);
// depthwise
GGML_API struct ggml_tensor * ggml_conv_2d_dw(
struct ggml_context * ctx,
struct ggml_tensor * a, // convolution kernel
struct ggml_tensor * b, // data
int s0, // stride dimension 0
int s1, // stride dimension 1
int p0, // padding dimension 0
int p1, // padding dimension 1
int d0, // dilation dimension 0
int d1); // dilation dimension 1
GGML_API struct ggml_tensor * ggml_conv_transpose_2d_p0(
struct ggml_context * ctx,
struct ggml_tensor * a,