{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.12.0-rc1\n"
]
}
],
"source": [
"import os\n",
"import tensorflow as tf\n",
"print(tf.__version__)\n",
"os.chdir(\"TensorFlowTTS\")\n",
"os.system(\"pip install .\")\n",
"os.chdir(\"..\")\n",
"import sys\n",
"sys.path.append(\"TensorFlowTTS/\")\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: h5py in c:\\users\\sathishreddy\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (3.8.0)\n",
"Requirement already satisfied: numpy>=1.14.5 in c:\\users\\sathishreddy\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from h5py) (1.23.5)\n"
]
}
],
"source": [
"!pip install h5py"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (b) MelGAN + STFT Loss"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading MelGAN-STFT model...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\sathishreddy\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\gdown\\cli.py:126: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From: https://drive.google.com/uc?id=1WB5iQbk9qB-Y-wO8BU6S2TnRiu4VU5ys\n",
"To: c:\\Users\\sathishreddy\\Desktop\\SpeechProcessing_EndSem_Proj\\melgan.stft-2M.h5\n",
"\n",
" 0%| | 0.00/17.1M [00:00, ?B/s]\n",
" 3%|▎ | 524k/17.1M [00:01<00:47, 350kB/s]\n",
" 6%|▌ | 1.05M/17.1M [00:02<00:30, 535kB/s]\n",
" 9%|▉ | 1.57M/17.1M [00:03<00:28, 544kB/s]\n",
" 12%|█▏ | 2.10M/17.1M [00:03<00:23, 637kB/s]\n",
" 15%|█▌ | 2.62M/17.1M [00:04<00:22, 650kB/s]\n",
" 18%|█▊ | 3.15M/17.1M [00:05<00:21, 650kB/s]\n",
" 21%|██▏ | 3.67M/17.1M [00:06<00:25, 524kB/s]\n",
" 24%|██▍ | 4.19M/17.1M [00:07<00:26, 493kB/s]\n",
" 28%|██▊ | 4.72M/17.1M [00:08<00:24, 510kB/s]\n",
" 31%|███ | 5.24M/17.1M [00:09<00:21, 556kB/s]\n",
" 34%|███▎ | 5.77M/17.1M [00:10<00:18, 611kB/s]\n",
" 37%|███▋ | 6.29M/17.1M [00:11<00:17, 612kB/s]\n",
" 40%|███▉ | 6.82M/17.1M [00:11<00:15, 651kB/s]\n",
" 43%|████▎ | 7.34M/17.1M [00:12<00:15, 637kB/s]\n",
" 46%|████▌ | 7.86M/17.1M [00:13<00:14, 629kB/s]\n",
" 49%|████▉ | 8.39M/17.1M [00:14<00:14, 621kB/s]\n",
" 52%|█████▏ | 8.91M/17.1M [00:15<00:13, 602kB/s]\n",
" 55%|█████▌ | 9.44M/17.1M [00:16<00:13, 587kB/s]\n",
" 58%|█████▊ | 9.96M/17.1M [00:17<00:14, 508kB/s]\n",
" 61%|██████ | 10.5M/17.1M [00:18<00:13, 488kB/s]\n",
" 64%|██████▍ | 11.0M/17.1M [00:19<00:11, 539kB/s]\n",
" 67%|██████▋ | 11.5M/17.1M [00:20<00:10, 557kB/s]\n",
" 70%|███████ | 12.1M/17.1M [00:21<00:08, 588kB/s]\n",
" 73%|███████▎ | 12.6M/17.1M [00:22<00:07, 576kB/s]\n",
" 76%|███████▋ | 13.1M/17.1M [00:23<00:07, 507kB/s]\n",
" 80%|███████▉ | 13.6M/17.1M [00:24<00:07, 501kB/s]\n",
" 83%|████████▎ | 14.2M/17.1M [00:25<00:05, 506kB/s]\n",
" 86%|████████▌ | 14.7M/17.1M [00:27<00:06, 393kB/s]\n",
" 89%|████████▊ | 15.2M/17.1M [00:29<00:05, 362kB/s]\n",
" 92%|█████████▏| 15.7M/17.1M [00:30<00:03, 381kB/s]\n",
" 95%|█████████▍| 16.3M/17.1M [00:31<00:02, 369kB/s]\n",
" 98%|█████████▊| 16.8M/17.1M [00:33<00:00, 389kB/s]\n",
"100%|██████████| 17.1M/17.1M [00:34<00:00, 356kB/s]\n",
"100%|██████████| 17.1M/17.1M [00:34<00:00, 497kB/s]\n",
"c:\\Users\\sathishreddy\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\gdown\\cli.py:126: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From: https://drive.google.com/uc?id=1OqdrcHJvtXwNasEZP7KXZwtGUDXMKNkg\n",
"To: c:\\Users\\sathishreddy\\Desktop\\SpeechProcessing_EndSem_Proj\\melgan.stft_config.yml\n",
"\n",
" 0%| | 0.00/1.77k [00:00, ?B/s]\n",
"100%|██████████| 1.77k/1.77k [00:00, ?B/s]\n"
]
}
],
"source": [
"print(\"Downloading MelGAN-STFT model...\")\n",
"!gdown --id {\"1WB5iQbk9qB-Y-wO8BU6S2TnRiu4VU5ys\"} -O melgan.stft-2M.h5\n",
"!gdown --id {\"1OqdrcHJvtXwNasEZP7KXZwtGUDXMKNkg\"} -O melgan.stft_config.yml"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Model"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\sathishreddy\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\tensorflow_addons\\utils\\tfa_eol_msg.py:23: UserWarning: \n",
"\n",
"TensorFlow Addons (TFA) has ended development and introduction of new features.\n",
"TFA has entered a minimal maintenance and release mode until a planned end of life in May 2024.\n",
"Please modify downstream libraries to take dependencies from other repositories in our TensorFlow community (e.g. Keras, Keras-CV, and Keras-NLP). \n",
"\n",
"For more information see: https://github.com/tensorflow/addons/issues/2807 \n",
"\n",
" warnings.warn(\n",
"c:\\Users\\sathishreddy\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"import tensorflow as tf\n",
"\n",
"import yaml\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import IPython.display as ipd\n",
"\n",
"from tensorflow_tts.inference import TFAutoModel\n",
"from tensorflow_tts.inference import AutoConfig\n",
"from tensorflow_tts.inference import AutoProcessor"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (a) Tacotron 2"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\sathishreddy\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\huggingface_hub\\file_download.py:649: FutureWarning: 'cached_download' is the legacy way to download files from the HF hub, please consider upgrading to 'hf_hub_download'\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n",
"WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n"
]
}
],
"source": [
"tacotron2 = TFAutoModel.from_pretrained(\"tensorspeech/tts-tacotron2-ljspeech-en\", name=\"tacotron2\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (b) FastSpeech"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"fastspeech = TFAutoModel.from_pretrained(\"tensorspeech/tts-fastspeech-ljspeech-en\", name=\"fastspeech\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (c) FastSpeech2"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"fastspeech2 = TFAutoModel.from_pretrained(\"tensorspeech/tts-fastspeech2-ljspeech-en\", name=\"fastspeech2\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (d) MelGAN Original"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"melgan = TFAutoModel.from_pretrained(\"tensorspeech/tts-melgan-ljspeech-en\", name=\"melgan\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (e) MelGAN STFT"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"melgan_stft_config = AutoConfig.from_pretrained('TensorFlowTTS/examples/melgan_stft/conf/melgan_stft.v1.yaml')\n",
"melgan_stft = TFAutoModel.from_pretrained(\n",
" config=melgan_stft_config,\n",
" pretrained_path=\"melgan.stft-2M.h5\",\n",
" name=\"melgan_stft\"\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (f) Multi-band MelGAN"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"mb_melgan = TFAutoModel.from_pretrained(\"tensorspeech/tts-mb_melgan-ljspeech-en\", name=\"mb_melgan\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"processor = AutoProcessor.from_pretrained(\"tensorspeech/tts-tacotron2-ljspeech-en\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"def do_synthesis(input_text, text2mel_model, vocoder_model, text2mel_name, vocoder_name):\n",
" input_ids = processor.text_to_sequence(input_text)\n",
"\n",
" # text2mel part\n",
" if text2mel_name == \"TACOTRON\":\n",
" _, mel_outputs, stop_token_prediction, alignment_history = text2mel_model.inference(\n",
" tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),\n",
" tf.convert_to_tensor([len(input_ids)], tf.int32),\n",
" tf.convert_to_tensor([0], dtype=tf.int32)\n",
" )\n",
" elif text2mel_name == \"FASTSPEECH\":\n",
" mel_before, mel_outputs, duration_outputs = text2mel_model.inference(\n",
" input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),\n",
" speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),\n",
" speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),\n",
" )\n",
" elif text2mel_name == \"FASTSPEECH2\":\n",
" mel_before, mel_outputs, duration_outputs, _, _ = text2mel_model.inference(\n",
" tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),\n",
" speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),\n",
" speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),\n",
" f0_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),\n",
" energy_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),\n",
" )\n",
" else:\n",
" raise ValueError(\"Only TACOTRON, FASTSPEECH, FASTSPEECH2 are supported on text2mel_name\")\n",
"\n",
" # vocoder part\n",
" if vocoder_name == \"MELGAN\" or vocoder_name == \"MELGAN-STFT\":\n",
" audio = vocoder_model(mel_outputs)[0, :, 0]\n",
" elif vocoder_name == \"MB-MELGAN\":\n",
" audio = vocoder_model(mel_outputs)[0, :, 0]\n",
" else:\n",
" raise ValueError(\"Only MELGAN, MELGAN-STFT and MB_MELGAN are supported on vocoder_name\")\n",
"\n",
" if text2mel_name == \"TACOTRON\":\n",
" return mel_outputs.numpy(), alignment_history.numpy(), audio.numpy()\n",
" else:\n",
" return mel_outputs.numpy(), audio.numpy()\n",
"\n",
"def visualize_attention(alignment_history):\n",
" import matplotlib.pyplot as plt\n",
"\n",
" fig = plt.figure(figsize=(8, 6))\n",
" ax = fig.add_subplot(111)\n",
" ax.set_title(f'Alignment steps')\n",
" im = ax.imshow(\n",
" alignment_history,\n",
" aspect='auto',\n",
" origin='lower',\n",
" interpolation='none')\n",
" fig.colorbar(im, ax=ax)\n",
" xlabel = 'Decoder timestep'\n",
" plt.xlabel(xlabel)\n",
" plt.ylabel('Encoder timestep')\n",
" plt.tight_layout()\n",
" plt.show()\n",
" plt.close()\n",
"\n",
"def visualize_mel_spectrogram(mels):\n",
" mels = tf.reshape(mels, [-1, 80]).numpy()\n",
" fig = plt.figure(figsize=(10, 8))\n",
" ax1 = fig.add_subplot(311)\n",
" ax1.set_title(f'Predicted Mel-after-Spectrogram')\n",
" im = ax1.imshow(np.rot90(mels), aspect='auto', interpolation='none')\n",
" fig.colorbar(mappable=im, shrink=0.65, orientation='horizontal', ax=ax1)\n",
" plt.show()\n",
" plt.close()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"input_text = \"Kashmir is India's paradise.\""
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (a) Tacotron2 + MELGAN"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mels, alignment_history, audios = do_synthesis(input_text, tacotron2, melgan, \"TACOTRON\", \"MELGAN\")\n",
"#visualize_attention(alignment_history[0])\n",
"#visualize_mel_spectrogram(mels[0])\n",
"ipd.Audio(audios, rate=22050)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (b) Tacotron2 + MELGAN-STFT"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mels, alignment_history, audios = do_synthesis(input_text, tacotron2, melgan_stft, \"TACOTRON\", \"MELGAN-STFT\")\n",
"#visualize_attention(alignment_history[0])\n",
"#visualize_mel_spectrogram(mels[0])\n",
"ipd.Audio(audios, rate=22050)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (c) Tacotron2 + MB-MELGAN"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mels, alignment_history, audios = do_synthesis(input_text, tacotron2, mb_melgan, \"TACOTRON\", \"MB-MELGAN\")\n",
"#visualize_attention(alignment_history[0])\n",
"#visualize_mel_spectrogram(mels[0])\n",
"ipd.Audio(audios, rate=22050)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### (d) FastSpeech + MB-MELGAN"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"