8000 updates to dataset analysis notebooks by jreus · Pull Request #1853 · coqui-ai/TTS · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

updates to dataset analysis notebooks #1853

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 15, 2022
Merged

updates to dataset analysis notebooks #1853

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 12 additions & 9 deletions notebooks/dataset_analysis/AnalyzeDataset.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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",
")"
]
},
Expand All @@ -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"
]
},
Expand All @@ -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])"
]
Expand All @@ -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)"
Expand Down Expand Up @@ -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",
Expand Down Expand Up @@ -416,7 +419,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.5"
"version": "3.9.12"
}
},
"nbformat": 4,
Expand Down
25 changes: 15 additions & 10 deletions notebooks/dataset_analysis/PhonemeCoverage.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"
]
},
{
Expand All @@ -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"
]
},
{
Expand All @@ -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",
Expand All @@ -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)"
]
},
{
Expand Down Expand Up @@ -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"
Expand Down Expand Up @@ -229,7 +234,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
Expand All @@ -243,7 +248,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
"version": "3.9.12"
}
},
"nbformat": 4,
Expand Down
0