whispercpp 1.3.6 → 1.3.7

data/ext/sources/examples/talk-llama/models/t5-enc.cpp

@@ -1,96 +0,0 @@
-#include "models.h"
-
-llm_build_t5_enc::llm_build_t5_enc(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
-    const int64_t n_embd_head = hparams.n_embd_head_v();
-
-    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k());
-
-    ggml_tensor * cur;
-    ggml_tensor * inpL;
-
-    inpL = build_inp_embd(model.tok_embd);
-
-    ggml_tensor * pos_bucket_enc = build_inp_pos_bucket_enc();
-
-    auto * inp_attn = build_attn_inp_no_cache();
-
-    ggml_tensor * inp_out_ids = build_inp_out_ids();
-
-    for (int il = 0; il < n_layer; ++il) {
-        ggml_tensor * inpSA = inpL;
-
-        // norm
-        cur = build_norm(inpL,
-                model.layers[il].attn_norm_enc, NULL,
-                LLM_NORM_RMS, il);
-        cb(cur, "attn_norm", il);
-
-        // self-attention
-        {
-            ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq_enc, cur);
-            cb(Qcur, "Qcur", il);
-
-            ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk_enc, cur);
-            cb(Kcur, "Kcur", il);
-
-            ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv_enc, cur);
-            cb(Vcur, "Vcur", il);
-
-            Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
-            Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
-            Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
-
-            ggml_tensor * attn_rel_b = model.layers[il].attn_rel_b_enc ? model.layers[il].attn_rel_b_enc : model.layers[0].attn_rel_b_enc;
-            ggml_tensor * kq_b = build_pos_bias(pos_bucket_enc, attn_rel_b);
-
-            cur = build_attn(inp_attn,
-                    model.layers[il].wo_enc, nullptr,
-                    Qcur, Kcur, Vcur, kq_b, nullptr, nullptr, 1.0f, il);
-            cb(cur, "kqv_out", il);
-        }
-        if (il == n_layer - 1 && inp_out_ids) {
-            cur   = ggml_get_rows(ctx0,   cur, inp_out_ids);
-            inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
-        }
-        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
-        cb(ffn_inp, "ffn_inp", il);
-
-        // feed-forward network
-        {
-            cur = build_norm(ffn_inp,
-                    model.layers[il].ffn_norm_enc, NULL,
-                    LLM_NORM_RMS, il);
-            cb(cur, "ffn_norm", il);
-
-            // T5 uses relu, flan-T5 uses gelu-gated
-            cur = build_ffn(cur,
-                    model.layers[il].ffn_up_enc,   NULL, NULL,
-                    model.layers[il].ffn_gate_enc, NULL, NULL,
-                    model.layers[il].ffn_down_enc, NULL, NULL,
-                    NULL,
-                    model.layers[il].ffn_gate_enc ? LLM_FFN_GELU : LLM_FFN_RELU,
-                    model.layers[il].ffn_gate_enc ? LLM_FFN_PAR  : LLM_FFN_SEQ,
-                    il);
-            cb(cur, "ffn_out", il);
-        }
-        cur = ggml_add(ctx0, cur, ffn_inp);
-        cb(cur, "ffn_out", il);
-
-        cur = build_cvec(cur, il);
-        cb(cur, "l_out", il);
-
-        // input for next layer
-        inpL = cur;
-    }
-    cur = inpL;
-    cb(cur, "result_embd", -1);
-
-    cur = build_norm(cur,
-            model.output_norm_enc, NULL,
-            LLM_NORM_RMS, -1);
-
-    cb(cur, "result_norm", -1);
-    res->t_embd = cur;
-
-    ggml_build_forward_expand(gf, cur);
-}

data/ext/sources/examples/talk-llama/models/wavtokenizer-dec.cpp

@@ -1,149 +0,0 @@
-#include "models.h"
-
-llm_build_wavtokenizer_dec::llm_build_wavtokenizer_dec(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
-    ggml_tensor * cur;
-    ggml_tensor * inpL;
-
-    inpL = build_inp_embd(model.tok_embd);
-
-    cur = ggml_cont(ctx0, ggml_transpose(ctx0, inpL));
-
-    cur = ggml_conv_1d_ph(ctx0, model.conv1d, cur, 1, 1);
-    cur = ggml_add(ctx0, cur, model.conv1d_b);
-
-    // posnet
-    for (uint32_t il = 0; il < hparams.posnet.n_layer; ++il) {
-        const auto & layer = model.layers[il].posnet;
-
-        inpL = cur;
-
-        switch (il) {
-            case 0:
-            case 1:
-            case 3:
-            case 4:
-                {
-                    cur = build_norm(cur,
-                            layer.norm1,
-                            layer.norm1_b,
-                            LLM_NORM_GROUP, 0);
-
-                    cur = ggml_mul(ctx0, ggml_sigmoid(ctx0, cur), cur);
-
-                    cur = ggml_conv_1d_ph(ctx0, layer.conv1, cur, 1, 1);
-                    cur = ggml_add(ctx0, cur, layer.conv1_b);
-
-                    cur = build_norm(cur,
-                            layer.norm2,
-                            layer.norm2_b,
-                            LLM_NORM_GROUP, 0);
-
-                    cur = ggml_mul(ctx0, ggml_sigmoid(ctx0, cur), cur);
-
-                    cur = ggml_conv_1d_ph(ctx0, layer.conv2, cur, 1, 1);
-                    cur = ggml_add(ctx0, cur, layer.conv2_b);
-
-                    cur = ggml_add(ctx0, cur, inpL);
-                } break;
-            case 2:
-                {
-                    cur = build_norm(cur,
-                            layer.attn_norm,
-                            layer.attn_norm_b,
-                            LLM_NORM_GROUP, 0);
-
-                    ggml_tensor * q;
-                    ggml_tensor * k;
-                    ggml_tensor * v;
-
-                    q = ggml_conv_1d_ph(ctx0, layer.attn_q, cur, 1, 1);
-                    k = ggml_conv_1d_ph(ctx0, layer.attn_k, cur, 1, 1);
-                    v = ggml_conv_1d_ph(ctx0, layer.attn_v, cur, 1, 1);
-
-                    q = ggml_add(ctx0, q, layer.attn_q_b);
-                    k = ggml_add(ctx0, k, layer.attn_k_b);
-                    v = ggml_add(ctx0, v, layer.attn_v_b);
-
-                    q = ggml_cont(ctx0, ggml_transpose(ctx0, q));
-                    k = ggml_cont(ctx0, ggml_transpose(ctx0, k));
-
-                    ggml_tensor * kq = ggml_mul_mat(ctx0, k, q);
-
-                    kq = ggml_soft_max_ext(ctx0, kq, nullptr, 1.0f/sqrtf(float(hparams.posnet.n_embd)), 0.0f);
-
-                    cur = ggml_mul_mat(ctx0, kq, v);
-
-                    cur = ggml_conv_1d_ph(ctx0, layer.attn_o, cur, 1, 1);
-                    cur = ggml_add(ctx0, cur, layer.attn_o_b);
-
-                    cur = ggml_add(ctx0, cur, inpL);
-                } break;
-            case 5:
-                {
-                    cur = build_norm(cur,
-                            layer.norm,
-                            layer.norm_b,
-                            LLM_NORM_GROUP, 0);
-                } break;
-            default: GGML_ABORT("unknown posnet layer");
-        };
-    }
-    cur = ggml_cont(ctx0, ggml_transpose(ctx0, cur));
-
-    cur = build_norm(cur,
-            model.tok_norm,
-            model.tok_norm_b,
-            LLM_NORM, -1);
-
-    cur = ggml_cont(ctx0, ggml_transpose(ctx0, cur));
-
-    inpL = cur;
-
-    // convnext
-    for (uint32_t il = 0; il < hparams.convnext.n_layer; ++il) {
-        const auto & layer = model.layers[il].convnext;
-
-        cur = inpL;
-
-        cur = ggml_conv_1d_dw_ph(ctx0, layer.dw, cur, 1, 1);
-        cur = ggml_add(ctx0, cur, layer.dw_b);
-
-        cur = ggml_cont(ctx0, ggml_transpose(ctx0, cur));
-
-        cur = build_norm(cur,
-                layer.norm,
-                layer.norm_b,
-                LLM_NORM, -1);
-
-        cur = build_ffn(cur,
-                layer.pw1, layer.pw1_b, NULL,
-                NULL,      NULL,        NULL,
-                layer.pw2, layer.pw2_b, NULL,
-                NULL,
-                LLM_FFN_GELU, LLM_FFN_SEQ, il);
-
-        cur = ggml_mul(ctx0, cur, layer.gamma);
-
-        cur = ggml_cont(ctx0, ggml_transpose(ctx0, cur));
-
-        inpL = ggml_add(ctx0, cur, inpL);
-    }
-    cur = inpL;
-
-    cur = ggml_cont(ctx0, ggml_transpose(ctx0, cur));
-
-    cur = build_norm(cur,
-            model.output_norm,
-            model.output_norm_b,
-            LLM_NORM, -1);
-
-    // lm_head
-    cur = build_lora_mm(model.output, cur);
-
-    cur = ggml_add(ctx0, cur, model.output_b);
-
-    cb(cur, "result_embd", -1);
-    res->t_embd = cur;
-
-    ggml_build_forward_expand(gf, cur);
-}

data/ext/sources/examples/talk-llama/models/xverse.cpp

@@ -1,108 +0,0 @@
-#include "models.h"
-
-llm_build_xverse::llm_build_xverse(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
-    const int64_t n_embd_head = hparams.n_embd_head_v();
-
-    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k());
-    GGML_ASSERT(n_embd_head == n_rot);
-
-    ggml_tensor * cur;
-    ggml_tensor * inpL;
-
-    inpL = build_inp_embd(model.tok_embd);
-
-    // inp_pos - contains the positions
-    ggml_tensor * inp_pos = build_inp_pos();
-
-    auto * inp_attn = build_attn_inp_kv();
-
-    ggml_tensor * inp_out_ids = build_inp_out_ids();
-
-    for (int il = 0; il < n_layer; ++il) {
-        ggml_tensor * inpSA = inpL;
-
-        cur = build_norm(inpL,
-                model.layers[il].attn_norm, NULL,
-                LLM_NORM_RMS, il);
-        cb(cur, "attn_norm", il);
-
-        // self-attention
-        {
-            ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
-            cb(Qcur, "Qcur", il);
-
-            ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
-            cb(Kcur, "Kcur", il);
-
-            ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
-            cb(Vcur, "Vcur", il);
-
-            Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
-            Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
-            Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
-
-            Qcur = ggml_rope_ext(
-                    ctx0, Qcur, inp_pos, nullptr,
-                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
-                    ext_factor, attn_factor, beta_fast, beta_slow
-                    );
-
-            Kcur = ggml_rope_ext(
-                    ctx0, Kcur, inp_pos, nullptr,
-                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
-                    ext_factor, attn_factor, beta_fast, beta_slow
-                    );
-
-            cb(Qcur, "Qcur", il);
-            cb(Kcur, "Kcur", il);
-            cb(Vcur, "Vcur", il);
-
-            cur = build_attn(inp_attn,
-                    model.layers[il].wo, NULL,
-                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
-        }
-        if (il == n_layer - 1 && inp_out_ids) {
-            cur   = ggml_get_rows(ctx0,   cur, inp_out_ids);
-            inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
-        }
-        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
-        cb(ffn_inp, "ffn_inp", il);
-
-        // feed-forward network
-        {
-            cur = build_norm(ffn_inp,
-                    model.layers[il].ffn_norm, NULL,
-                    LLM_NORM_RMS, il);
-            cb(cur, "ffn_norm", il);
-
-            cur = build_ffn(cur,
-                    model.layers[il].ffn_up,   NULL, NULL,
-                    model.layers[il].ffn_gate, NULL, NULL,
-                    model.layers[il].ffn_down, NULL, NULL,
-                    NULL,
-                    LLM_FFN_SILU, LLM_FFN_PAR, il);
-            cb(cur, "ffn_out", il);
-        }
-        cur = ggml_add(ctx0, cur, ffn_inp);
-
-        cur = build_cvec(cur, il);
-        cb(cur, "l_out", il);
-
-        // input for next layer
-        inpL = cur;
-    }
-    cur = inpL;
-
-    cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
-
-    cb(cur, "result_norm", -1);
-    res->t_embd = cur;
-
-    // lm_head
-    cur = build_lora_mm(model.output, cur);
-
-    cb(cur, "result_output", -1);
-    res->t_logits = cur;
-
-    ggml_build_forward_expand(gf, cur);
-}

data/ext/sources/examples/talk-llama/prompts/talk-alpaca.txt

@@ -1,23 +0,0 @@
-Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-
-Write a text transcript of a never ending dialog, where {0} interacts with an AI assistant named {1}.
-{1} is helpful, kind, honest, friendly, good at writing and never fails to answer {0}’s requests immediately and with details and precision.
-There are no annotations like (30 seconds passed...) or (to himself), just what {0} and {1} say aloud to each other.
-The transcript only includes text, it does not include markup like HTML and Markdown.
-{1} responds with short and concise answers.
-
-### Response:
-
-{0}{4} Hello, {1}!
-{1}{4} Hello {0}! How may I help you today?
-{0}{4} What time is it?
-{1}{4} It is {2} o'clock.
-{0}{4} What year is it?
-{1}{4} We are in {3}.
-{0}{4} What is a cat?
-{1}{4} A cat is a domestic species of small carnivorous mammal. It is the only domesticated species in the family Felidae.
-{0}{4} Name a color.
-{1}{4} Blue
-{0}{4}

data/ext/sources/examples/talk-llama/speak

@@ -1,40 +0,0 @@
-#!/bin/bash
-
-# Usage:
-#  speak <voice_id> <textfile>
-
-function installed() { command -v $1 >/dev/null 2>&1; }
-
-if installed espeak; then
-  espeak -v en-us+m$1 -s 225 -p 50 -a 200 -g 5 -k 5 -f $2
-
-elif installed piper && installed aplay; then
-  cat $2 | piper --model ~/en_US-lessac-medium.onnx --output-raw | aplay -q -r 22050 -f S16_LE -t raw -
-
-# for Mac
-elif installed say; then
-  say -f $2
-
-# Eleven Labs
-elif installed python3 && \
-  python3 -c 'import importlib.util; exit(not importlib.util.find_spec("elevenlabs"))' && \
-  installed ffplay; then
-    # It's possible to use the API for free with limited number of characters.
-    # To increase this limit register to https://beta.elevenlabs.io to get an api key
-    # and paste it after 'ELEVEN_API_KEY='
-    # Keep the line commented to use the free version without api key
-    #export ELEVEN_API_KEY=your_api_key
-    wd=$(dirname $0)
-    script=$wd/eleven-labs.py
-    python3 $script -q -p -v $1 $2 >/dev/null 2>&1
-
-    # Uncomment to keep the audio file
-    #python3 $script -q -s ./audio.mp3 -v $1 $2 >/dev/null 2>&1
-    #ffplay -autoexit -nodisp -loglevel quiet -hide_banner -i ./audio.mp3 >/dev/null 2>&1
-
-else
-  echo 'Install espeak ("brew install espeak" or "apt-get install espeak"),'
-  echo 'piper ("pip install piper-tts" or https://github.com/rhasspy/piper) with aplay,'
-  echo 'or elevenlabs ("pip install elevenlabs") with ffplay.'
-  echo '(export ELEVEN_API_KEY if you have an api key from https://beta.elevenlabs.io)'
-fi

data/ext/sources/examples/talk-llama/speak.bat

@@ -1 +0,0 @@
-@powershell -ExecutionPolicy Bypass -F examples\talk-llama\speak.ps1 %1 %2

data/ext/sources/examples/talk-llama/speak.ps1

@@ -1,14 +0,0 @@
-# Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope CurrentUser
-param(
-  [Parameter(Mandatory=$true)][int]$voicenum,
-  [Parameter(Mandatory=$true)][string]$textfile
-)
-
-Add-Type -AssemblyName System.Speech;
-$speak = New-Object System.Speech.Synthesis.SpeechSynthesizer;
-$voiceoptions = $speak.GetInstalledVoices("en-US");
-$voice = $voiceoptions[$voicenum % $voiceoptions.count];
-$speak.SelectVoice($voice.VoiceInfo.Name);
-$speak.Rate="0";
-$text = Get-Content -Path $textfile;
-$speak.Speak($text);