updates to dataset analysis notebooks for compatibility with latest version of TTS (#1853)

notebooks/dataset_analysis/AnalyzeDataset.ipynb

@@ -45,7 +45,7 @@
    "source": [
     "NUM_PROC = 8\n",
     "DATASET_CONFIG = BaseDatasetConfig(\n",
-    "    name=\"ljspeech\", meta_file_train=\"metadata.csv\", path=\"/home/ubuntu/TTS/depot/data/male_dataset1_44k/\"\n",
+    "    name=\"ljspeech\", meta_file_train=\"metadata.csv\", path=\"/absolute/path/to/your/dataset/\"\n",
     ")"
    ]
   },
@@ -58,13 +58,13 @@
     "def formatter(root_path, meta_file, **kwargs):  # pylint: disable=unused-argument\n",
     "    txt_file = os.path.join(root_path, meta_file)\n",
     "    items = []\n",
-    "    speaker_name = \"maledataset1\"\n",
+    "    speaker_name = \"myspeaker\"\n",
     "    with open(txt_file, \"r\", encoding=\"utf-8\") as ttf:\n",
     "        for line in ttf:\n",
     "            cols = line.split(\"|\")\n",
-    "            wav_file = os.path.join(root_path, \"wavs\", cols[0])\n",
+    "            wav_file = os.path.join(root_path, \"wavs\", cols[0] + \".wav\")            \n",
     "            text = cols[1]\n",
-    "            items.append([text, wav_file, speaker_name])\n",
+    "            items.append({\"text\": text, \"audio_file\": wav_file, \"speaker_name\": speaker_name})\n",
     "    return items"
    ]
   },
@@ -78,7 +78,10 @@
    "source": [
     "# use your own preprocessor at this stage - TTS/datasets/proprocess.py\n",
     "train_samples, eval_samples = load_tts_samples(DATASET_CONFIG, eval_split=True, formatter=formatter)\n",
-    "items = train_samples + eval_samples\n",
+    "if eval_samples is not None:\n",
+    "    items = train_samples + eval_samples\n",
+    "else:\n",
+    "    items = train_samples\n",
     "print(\" > Number of audio files: {}\".format(len(items)))\n",
     "print(items[1])"
    ]
@@ -94,7 +97,7 @@
     "# check wavs if exist\n",
     "wav_files = []\n",
     "for item in items:\n",
-    "    wav_file = item[1].strip()\n",
+    "    wav_file = item[\"audio_file\"].strip()\n",
     "    wav_files.append(wav_file)\n",
     "    if not os.path.exists(wav_file):\n",
     "        print(waf_path)"
@@ -131,8 +134,8 @@
    "outputs": [],
    "source": [
     "def load_item(item):\n",
-    "    text = item[0].strip()\n",
-    "    file_name = item[1].strip()\n",
+    "    text = item[\"text\"].strip()\n",
+    "    file_name = item[\"audio_file\"].strip()\n",
     "    audio, sr = librosa.load(file_name, sr=None)\n",
     "    audio_len = len(audio) / sr\n",
     "    text_len = len(text)\n",
@@ -416,7 +419,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.5"
+   "version": "3.9.12"
   }
  },
  "nbformat": 4,

notebooks/dataset_analysis/PhonemeCoverage.ipynb

@@ -37,7 +37,7 @@
     "# set some vars\n",
     "# TTS_PATH = \"/home/thorsten/___dev/tts/mozilla/TTS\"\n",
     "CONFIG_FILE = \"/path/to/config/config.json\"\n",
-    "CHARS_TO_REMOVE = \".,:!?'\""
+    "CHARS_TO_REMOVE = \".,:!?'\"\n"
    ]
   },
   {
@@ -59,7 +59,8 @@
     "# extra imports that might not be included in requirements.txt\n",
     "import collections\n",
     "import operator\n",
-    "\n"
+    "\n",
+    "%matplotlib inline"
    ]
   },
   {
@@ -75,7 +76,7 @@
     "CONFIG = load_config(CONFIG_FILE)\n",
     "\n",
     "# Load some properties from config.json\n",
-    "CONFIG_METADATA = sorted(load_tts_samples(CONFIG.datasets)[0])\n",
+    "CONFIG_METADATA = load_tts_samples(CONFIG.datasets)[0]\n",
     "CONFIG_METADATA = CONFIG_METADATA\n",
     "CONFIG_DATASET = CONFIG.datasets[0]\n",
     "CONFIG_PHONEME_LANGUAGE = CONFIG.phoneme_language\n",
@@ -84,7 +85,10 @@
     "\n",
     "# Will be printed on generated output graph\n",
     "CONFIG_RUN_NAME = CONFIG.run_name\n",
-    "CONFIG_RUN_DESC = CONFIG.run_description"
+    "CONFIG_RUN_DESC = CONFIG.run_description\n",
+    "\n",
+    "# Needed to convert text to phonemes and phonemes to ids\n",
+    "tokenizer, config = TTSTokenizer.init_from_config(CONFIG)"
    ]
   },
   {
@@ -112,12 +116,13 @@
    "source": [
     "def get_phoneme_from_sequence(text):\n",
     "    temp_list = []\n",
-    "    if len(text[0]) > 0:\n",
-    "        temp_text = text[0].rstrip('\\n')\n",
+    "    if len(text[\"text\"]) > 0:\n",
+    "        #temp_text = text[0].rstrip('\\n')\n",
+    "        temp_text = text[\"text\"].rstrip('\\n')\n",
     "        for rm_bad_chars in CHARS_TO_REMOVE:\n",
     "            temp_text = temp_text.replace(rm_bad_chars,\"\")\n",
-    "        seq = phoneme_to_sequence(temp_text, [CONFIG_TEXT_CLEANER], CONFIG_PHONEME_LANGUAGE, CONFIG_ENABLE_EOS_BOS_CHARS)\n",
-    "        text = sequence_to_phoneme(seq)\n",
+    "        seq = tokenizer.text_to_ids(temp_text)\n",
+    "        text = tokenizer.ids_to_text(seq)\n",
     "        text = text.replace(\" \",\"\")\n",
     "        temp_list.append(text)\n",
     "    return temp_list"
@@ -229,7 +234,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -243,7 +248,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.12"
   }
  },
  "nbformat": 4,