mirror of https://github.com/coqui-ai/TTS.git
print model r value as loading it
This commit is contained in:
erogol
parent
48a40c4730
commit
e1eab1ce4b
|
|
@ -20,6 +20,7 @@ def load_checkpoint(model, checkpoint_path, amp=None, use_cuda=False):
|
|||
# set model stepsize
|
||||
if hasattr(model.decoder, 'r'):
|
||||
model.decoder.set_r(state['r'])
|
||||
print(" > Model r: ", state['r'])
|
||||
return model, state
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,316 +1,346 @@
|
|||
{
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"name": "DDC-TTS_and_MultiBand-MelGAN_TF_Example.ipynb",
|
||||
"provenance": [],
|
||||
"collapsed_sections": [],
|
||||
"toc_visible": true
|
||||
},
|
||||
"kernelspec": {
|
||||
"name": "python3",
|
||||
"display_name": "Python 3"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab_type": "text",
|
||||
"id": "6LWsNd3_M3MP"
|
||||
},
|
||||
"source": [
|
||||
"# Mozilla TTS on CPU Real-Time Speech Synthesis with Tensorflow"
|
||||
]
|
||||
},
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "6LWsNd3_M3MP",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"# Mozilla TTS on CPU Real-Time Speech Synthesis with Tensorflow"
|
||||
]
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab_type": "text",
|
||||
"id": "FAqrSIWgLyP0"
|
||||
},
|
||||
"source": [
|
||||
"**These models are converted from released [PyTorch models](https://colab.research.google.com/drive/1u_16ZzHjKYFn1HNVuA4Qf_i2MMFB9olY?usp=sharing) using our TF utilities provided in Mozilla TTS.**\n",
|
||||
"\n",
|
||||
"These TF models support TF 2.2 and for different versions you might need to\n",
|
||||
"regenerate them. \n",
|
||||
"\n",
|
||||
"We use Tacotron2 and MultiBand-Melgan models and LJSpeech dataset.\n",
|
||||
"\n",
|
||||
"Tacotron2 is trained using [Double Decoder Consistency](https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency/) (DDC) only for 130K steps (3 days) with a single GPU.\n",
|
||||
"\n",
|
||||
"MultiBand-Melgan is trained 1.45M steps with real spectrograms.\n",
|
||||
"\n",
|
||||
"Note that both model performances can be improved with more training.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab_type": "text",
|
||||
"id": "Ku-dA4DKoeXk"
|
||||
},
|
||||
"source": [
|
||||
"### Download Models"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 162
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "FAqrSIWgLyP0",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"**These models are converted from released [PyTorch models](https://colab.research.google.com/drive/1u_16ZzHjKYFn1HNVuA4Qf_i2MMFB9olY?usp=sharing) using our TF utilities provided in Mozilla TTS.**\n",
|
||||
"\n",
|
||||
"These TF models support TF 2.2 and for different versions you might need to\n",
|
||||
"regenerate them. \n",
|
||||
"\n",
|
||||
"We use Tacotron2 and MultiBand-Melgan models and LJSpeech dataset.\n",
|
||||
"\n",
|
||||
"Tacotron2 is trained using [Double Decoder Consistency](https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency/) (DDC) only for 130K steps (3 days) with a single GPU.\n",
|
||||
"\n",
|
||||
"MultiBand-Melgan is trained 1.45M steps with real spectrograms.\n",
|
||||
"\n",
|
||||
"Note that both model performances can be improved with more training.\n"
|
||||
]
|
||||
"colab_type": "code",
|
||||
"id": "jGIgnWhGsxU1",
|
||||
"outputId": "08b0dddd-4edf-48c9-e8e5-a419b36a5c3d",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!gdown --id 1p7OSEEW_Z7ORxNgfZwhMy7IiLE1s0aH7 -O data/tts_model.pkl\n",
|
||||
"!gdown --id 18CQ6G6tBEOfvCHlPqP8EBI4xWbrr9dBc -O data/config.json"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 235
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Ku-dA4DKoeXk",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"### Download Models"
|
||||
]
|
||||
"colab_type": "code",
|
||||
"id": "4dnpE0-kvTsu",
|
||||
"outputId": "2fe836eb-c7e7-4f1e-9352-0142126bb19f",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!gdown --id 1rHmj7CqD3Sfa716Y3ub_vpIBrQg_b1yF -O data/vocoder_model.pkl\n",
|
||||
"!gdown --id 1Rd0R_nRCrbjEdpOwq6XwZAktvugiBvmu -O data/config_vocoder.json\n",
|
||||
"!gdown --id 11oY3Tv0kQtxK_JPgxrfesa99maVXHNxU -O data/scale_stats.npy"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab_type": "text",
|
||||
"id": "Zlgi8fPdpRF0"
|
||||
},
|
||||
"source": [
|
||||
"### Define TTS function"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "f-Yc42nQZG5A"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def tts(model, text, CONFIG, p):\n",
|
||||
" t_1 = time.time()\n",
|
||||
" waveform, alignment, mel_spec, mel_postnet_spec, stop_tokens, inputs = synthesis(model, text, CONFIG, use_cuda, ap, speaker_id, style_wav=None,\n",
|
||||
" truncated=False, enable_eos_bos_chars=CONFIG.enable_eos_bos_chars,\n",
|
||||
" backend='tf')\n",
|
||||
" waveform = vocoder_model.inference(torch.FloatTensor(mel_postnet_spec.T).unsqueeze(0))\n",
|
||||
" waveform = waveform.numpy()[0, 0]\n",
|
||||
" rtf = (time.time() - t_1) / (len(waveform) / ap.sample_rate)\n",
|
||||
" tps = (time.time() - t_1) / len(waveform)\n",
|
||||
" print(waveform.shape)\n",
|
||||
" print(\" > Run-time: {}\".format(time.time() - t_1))\n",
|
||||
" print(\" > Real-time factor: {}\".format(rtf))\n",
|
||||
" print(\" > Time per step: {}\".format(tps))\n",
|
||||
" IPython.display.display(IPython.display.Audio(waveform, rate=CONFIG.audio['sample_rate'])) \n",
|
||||
" return alignment, mel_postnet_spec, stop_tokens, waveform"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab_type": "text",
|
||||
"id": "ZksegYQepkFg"
|
||||
},
|
||||
"source": [
|
||||
"### Load Models"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "oVa0kOamprgj"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import torch\n",
|
||||
"import time\n",
|
||||
"import IPython\n",
|
||||
"\n",
|
||||
"from TTS.tts.tf.utils.generic_utils import setup_model\n",
|
||||
"from TTS.tts.tf.utils.io import load_checkpoint\n",
|
||||
"from TTS.utils.io import load_config\n",
|
||||
"from TTS.tts.utils.text.symbols import symbols, phonemes\n",
|
||||
"from TTS.utils.audio import AudioProcessor\n",
|
||||
"from TTS.tts.utils.synthesis import synthesis"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "EY-sHVO8IFSH"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# runtime settings\n",
|
||||
"use_cuda = False"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "_1aIUp2FpxOQ"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# model paths\n",
|
||||
"TTS_MODEL = \"data/tts_model.pkl\"\n",
|
||||
"TTS_CONFIG = \"data/config.json\"\n",
|
||||
"VOCODER_MODEL = \"data/vocoder_model.pkl\"\n",
|
||||
"VOCODER_CONFIG = \"data/config_vocoder.json\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "CpgmdBVQplbv"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# load configs\n",
|
||||
"TTS_CONFIG = load_config(TTS_CONFIG)\n",
|
||||
"VOCODER_CONFIG = load_config(VOCODER_CONFIG)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 471
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "jGIgnWhGsxU1",
|
||||
"colab_type": "code",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 162
|
||||
},
|
||||
"outputId": "08b0dddd-4edf-48c9-e8e5-a419b36a5c3d",
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"!gdown --id 1p7OSEEW_Z7ORxNgfZwhMy7IiLE1s0aH7 -O data/tts_model.pkl\n",
|
||||
"!gdown --id 18CQ6G6tBEOfvCHlPqP8EBI4xWbrr9dBc -O data/config.json"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
"colab_type": "code",
|
||||
"id": "zmrQxiozIUVE",
|
||||
"outputId": "fa71bd05-401f-4e5b-a6f7-60ae765966db",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# load the audio processor\n",
|
||||
"TTS_CONFIG.audio['stats_path'] = 'data/scale_stats.npy'\n",
|
||||
"ap = AudioProcessor(**TTS_CONFIG.audio) "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 72
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "4dnpE0-kvTsu",
|
||||
"colab_type": "code",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 235
|
||||
},
|
||||
"outputId": "2fe836eb-c7e7-4f1e-9352-0142126bb19f",
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"!gdown --id 1rHmj7CqD3Sfa716Y3ub_vpIBrQg_b1yF -O data/vocoder_model.pkl\n",
|
||||
"!gdown --id 1Rd0R_nRCrbjEdpOwq6XwZAktvugiBvmu -O data/config_vocoder.json\n",
|
||||
"!gdown --id 11oY3Tv0kQtxK_JPgxrfesa99maVXHNxU -O data/scale_stats.npy"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
"colab_type": "code",
|
||||
"id": "8fLoI4ipqMeS",
|
||||
"outputId": "595d990f-930d-4698-ee14-77796b5eed7d",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# LOAD TTS MODEL\n",
|
||||
"# multi speaker \n",
|
||||
"speaker_id = None\n",
|
||||
"speakers = []\n",
|
||||
"\n",
|
||||
"# load the model\n",
|
||||
"num_chars = len(phonemes) if TTS_CONFIG.use_phonemes else len(symbols)\n",
|
||||
"model = setup_model(num_chars, len(speakers), TTS_CONFIG)\n",
|
||||
"model.build_inference()\n",
|
||||
"model = load_checkpoint(model, TTS_MODEL)\n",
|
||||
"model.decoder.set_max_decoder_steps(1000)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 489
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Zlgi8fPdpRF0",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"### Define TTS function"
|
||||
]
|
||||
"colab_type": "code",
|
||||
"id": "zKoq0GgzqzhQ",
|
||||
"outputId": "2cc3deae-144f-4465-da3b-98628d948506"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from TTS.vocoder.tf.utils.generic_utils import setup_generator\n",
|
||||
"from TTS.vocoder.tf.utils.io import load_checkpoint\n",
|
||||
"\n",
|
||||
"# LOAD VOCODER MODEL\n",
|
||||
"vocoder_model = setup_generator(VOCODER_CONFIG)\n",
|
||||
"vocoder_model.build_inference()\n",
|
||||
"vocoder_model = load_checkpoint(vocoder_model, VOCODER_MODEL)\n",
|
||||
"vocoder_model.inference_padding = 0\n",
|
||||
"\n",
|
||||
"ap_vocoder = AudioProcessor(**VOCODER_CONFIG['audio']) "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab_type": "text",
|
||||
"id": "Ws_YkPKsLgo-"
|
||||
},
|
||||
"source": [
|
||||
"## Run Inference"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 134
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "f-Yc42nQZG5A",
|
||||
"colab_type": "code",
|
||||
"colab": {}
|
||||
},
|
||||
"source": [
|
||||
"def tts(model, text, CONFIG, p):\n",
|
||||
" t_1 = time.time()\n",
|
||||
" waveform, alignment, mel_spec, mel_postnet_spec, stop_tokens, inputs = synthesis(model, text, CONFIG, use_cuda, ap, speaker_id, style_wav=None,\n",
|
||||
" truncated=False, enable_eos_bos_chars=CONFIG.enable_eos_bos_chars,\n",
|
||||
" backend='tf')\n",
|
||||
" waveform = vocoder_model.inference(torch.FloatTensor(mel_postnet_spec.T).unsqueeze(0))\n",
|
||||
" waveform = waveform.numpy()[0, 0]\n",
|
||||
" rtf = (time.time() - t_1) / (len(waveform) / ap.sample_rate)\n",
|
||||
" tps = (time.time() - t_1) / len(waveform)\n",
|
||||
" print(waveform.shape)\n",
|
||||
" print(\" > Run-time: {}\".format(time.time() - t_1))\n",
|
||||
" print(\" > Real-time factor: {}\".format(rtf))\n",
|
||||
" print(\" > Time per step: {}\".format(tps))\n",
|
||||
" IPython.display.display(IPython.display.Audio(waveform, rate=CONFIG.audio['sample_rate'])) \n",
|
||||
" return alignment, mel_postnet_spec, stop_tokens, waveform"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "ZksegYQepkFg",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"### Load Models"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "oVa0kOamprgj",
|
||||
"colab_type": "code",
|
||||
"colab": {}
|
||||
},
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import torch\n",
|
||||
"import time\n",
|
||||
"import IPython\n",
|
||||
"\n",
|
||||
"from TTS.tts.tf.utils.generic_utils import setup_model\n",
|
||||
"from TTS.tts.tf.utils.io import load_checkpoint\n",
|
||||
"from TTS.utils.io import load_config\n",
|
||||
"from TTS.tts.utils.text.symbols import symbols, phonemes\n",
|
||||
"from TTS.utils.audio import AudioProcessor\n",
|
||||
"from TTS.tts.utils.synthesis import synthesis"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "EY-sHVO8IFSH",
|
||||
"colab_type": "code",
|
||||
"colab": {}
|
||||
},
|
||||
"source": [
|
||||
"# runtime settings\n",
|
||||
"use_cuda = False"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "_1aIUp2FpxOQ",
|
||||
"colab_type": "code",
|
||||
"colab": {}
|
||||
},
|
||||
"source": [
|
||||
"# model paths\n",
|
||||
"TTS_MODEL = \"data/tts_model.pkl\"\n",
|
||||
"TTS_CONFIG = \"data/config.json\"\n",
|
||||
"VOCODER_MODEL = \"data/vocoder_model.pkl\"\n",
|
||||
"VOCODER_CONFIG = \"data/config_vocoder.json\""
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "CpgmdBVQplbv",
|
||||
"colab_type": "code",
|
||||
"colab": {}
|
||||
},
|
||||
"source": [
|
||||
"# load configs\n",
|
||||
"TTS_CONFIG = load_config(TTS_CONFIG)\n",
|
||||
"VOCODER_CONFIG = load_config(VOCODER_CONFIG)"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "zmrQxiozIUVE",
|
||||
"colab_type": "code",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 471
|
||||
},
|
||||
"outputId": "fa71bd05-401f-4e5b-a6f7-60ae765966db",
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"# load the audio processor\n",
|
||||
"TTS_CONFIG.audio['stats_path'] = 'data/scale_stats.npy'\n",
|
||||
"ap = AudioProcessor(**TTS_CONFIG.audio) "
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "8fLoI4ipqMeS",
|
||||
"colab_type": "code",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 72
|
||||
},
|
||||
"outputId": "595d990f-930d-4698-ee14-77796b5eed7d",
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"# LOAD TTS MODEL\n",
|
||||
"# multi speaker \n",
|
||||
"speaker_id = None\n",
|
||||
"speakers = []\n",
|
||||
"\n",
|
||||
"# load the model\n",
|
||||
"num_chars = len(phonemes) if TTS_CONFIG.use_phonemes else len(symbols)\n",
|
||||
"model = setup_model(num_chars, len(speakers), TTS_CONFIG)\n",
|
||||
"model.build_inference()\n",
|
||||
"model = load_checkpoint(model, TTS_MODEL)\n",
|
||||
"model.decoder.set_max_decoder_steps(1000)"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "zKoq0GgzqzhQ",
|
||||
"colab_type": "code",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 489
|
||||
},
|
||||
"outputId": "2cc3deae-144f-4465-da3b-98628d948506"
|
||||
},
|
||||
"source": [
|
||||
"from TTS.vocoder.tf.utils.generic_utils import setup_generator\n",
|
||||
"from TTS.vocoder.tf.utils.io import load_checkpoint\n",
|
||||
"\n",
|
||||
"# LOAD VOCODER MODEL\n",
|
||||
"vocoder_model = setup_generator(VOCODER_CONFIG)\n",
|
||||
"vocoder_model.build_inference()\n",
|
||||
"vocoder_model = load_checkpoint(vocoder_model, VOCODER_MODEL)\n",
|
||||
"vocoder_model.inference_padding = 0\n",
|
||||
"\n",
|
||||
"ap_vocoder = AudioProcessor(**VOCODER_CONFIG['audio']) "
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Ws_YkPKsLgo-",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"## Run Inference"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"id": "FuWxZ9Ey5Puj",
|
||||
"colab_type": "code",
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 134
|
||||
},
|
||||
"outputId": "07ede6e5-06e6-4612-f687-7984d20e5254"
|
||||
},
|
||||
"source": [
|
||||
"sentence = \"Bill got in the habit of asking himself “Is that thought true?” and if he wasn’t absolutely certain it was, he just let it go.\"\n",
|
||||
"align, spec, stop_tokens, wav = tts(model, sentence, TTS_CONFIG, ap)"
|
||||
],
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
}
|
||||
]
|
||||
}
|
||||
"colab_type": "code",
|
||||
"id": "FuWxZ9Ey5Puj",
|
||||
"outputId": "07ede6e5-06e6-4612-f687-7984d20e5254"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sentence = \"Bill got in the habit of asking himself “Is that thought true?” and if he wasn’t absolutely certain it was, he just let it go.\"\n",
|
||||
"align, spec, stop_tokens, wav = tts(model, sentence, TTS_CONFIG, ap)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"collapsed_sections": [],
|
||||
"name": "DDC-TTS_and_MultiBand-MelGAN_TF_Example.ipynb",
|
||||
"provenance": [],
|
||||
"toc_visible": true
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
|
|
|
|||
|
|
@ -181,7 +181,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.4"
|
||||
"version": "3.7.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
|
|
|||
|
|
@ -3,7 +3,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"TTS_PATH = \"/home/erogol/projects/\""
|
||||
|
|
@ -12,7 +14,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
|
|
@ -34,7 +38,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"DATA_PATH = \"/home/erogol/Data/m-ai-labs/de_DE/by_book/male/karlsson/\"\n",
|
||||
|
|
@ -58,7 +64,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# use your own preprocessor at this stage - TTS/datasets/proprocess.py\n",
|
||||
|
|
@ -69,7 +77,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# check wavs if exist\n",
|
||||
|
|
@ -84,7 +94,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# show duplicate items\n",
|
||||
|
|
@ -95,7 +107,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def load_item(item):\n",
|
||||
|
|
@ -121,7 +135,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# count words in the dataset\n",
|
||||
|
|
@ -136,7 +152,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"text_vs_durs = {} # text length vs audio duration\n",
|
||||
|
|
@ -155,7 +173,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# text_len vs avg_audio_len, median_audio_len, std_audio_len\n",
|
||||
|
|
@ -170,7 +190,9 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"source": [
|
||||
"### Avg audio length per char"
|
||||
]
|
||||
|
|
@ -178,7 +200,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for item in data:\n",
|
||||
|
|
@ -189,7 +213,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sec_per_chars = []\n",
|
||||
|
|
@ -205,7 +231,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mean = np.mean(sec_per_chars)\n",
|
||||
|
|
@ -217,7 +245,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dist = norm(mean, std)\n",
|
||||
|
|
@ -234,7 +264,9 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"source": [
|
||||
"### Plot Dataset Statistics"
|
||||
]
|
||||
|
|
@ -242,7 +274,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.title(\"text length vs mean audio duration\")\n",
|
||||
|
|
@ -252,7 +286,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.title(\"text length vs median audio duration\")\n",
|
||||
|
|
@ -262,7 +298,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.title(\"text length vs STD\")\n",
|
||||
|
|
@ -272,7 +310,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.title(\"text length vs # instances\")\n",
|
||||
|
|
@ -281,7 +321,9 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"source": [
|
||||
"### Check words frequencies"
|
||||
]
|
||||
|
|
@ -289,7 +331,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"w_count_df = pd.DataFrame.from_dict(w_count, orient='index')\n",
|
||||
|
|
@ -300,6 +344,7 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"Collapsed": "false",
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
|
|
@ -310,7 +355,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# check a certain word\n",
|
||||
|
|
@ -320,7 +367,9 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"Collapsed": "false"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# fequency bar plot - it takes time!!\n",
|
||||
|
|
@ -344,9 +393,9 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.2"
|
||||
"version": "3.7.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue