VoiceCraft/inference_speech_editing.ipynb

210 lines
8.3 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\" \n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/pyp/miniconda3/envs/voicecraft/lib/python3.9/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 libs\n",
"import torch\n",
"import torchaudio\n",
"\n",
"from data.tokenizer import (\n",
" AudioTokenizer,\n",
" TextTokenizer,\n",
")\n",
"\n",
"from models import voicecraft\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# hyperparameters for inference\n",
"left_margin = 0.08\n",
"right_margin = 0.08\n",
"seed = 1\n",
"codec_audio_sr = 16000\n",
"codec_sr = 50\n",
"top_k = 0\n",
"top_p = 0.8\n",
"temperature = 1\n",
"kvcache = 0\n",
"silence_tokens = [1388,1898,131]\n",
"stop_repetition = -1 # do not stop repetition on silence\n",
"device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
"\n",
"# point to the original file or record the file\n",
"# write down the transcript for the file, or run whisper to get the transcript (and you can modify it if it's not accurate), save it as a .txt file\n",
"orig_audio = \"./demo/84_121550_000074_000000.wav\"\n",
"orig_transcript = \"But when I had approached so near to them The common object, which the sense deceives, Lost not by distance any of its marks,\"\n",
"# move the audio and transcript to temp folder\n",
"temp_folder = \"./demo/temp\"\n",
"os.makedirs(temp_folder, exist_ok=True)\n",
"os.system(f\"cp {orig_audio} {temp_folder}\")\n",
"filename = os.path.splitext(orig_audio.split(\"/\")[-1])[0]\n",
"with open(f\"{temp_folder}/{filename}.txt\", \"w\") as f:\n",
" f.write(orig_transcript)\n",
"# run MFA to get the alignment\n",
"align_temp = f\"{temp_folder}/mfa_alignments\"\n",
"os.makedirs(align_temp, exist_ok=True)\n",
"os.system(f\"mfa align -j 1 --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp}\")\n",
"# if it fail, it could be because the audio is too hard for the alignment model, increasing the beam size usually solves the issue\n",
"# os.system(f\"mfa align -j 1 --output_format csv {temp_folder} english_us_arpa english_us_arpa {align_temp} --beam 1000 --retry_beam 2000\")\n",
"audio_fn = f\"{temp_folder}/{filename}.wav\"\n",
"transcript_fn = f\"{temp_folder}/{filename}.txt\"\n",
"align_fn = f\"{align_temp}/{filename}.csv\"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1)\n"
]
}
],
"source": [
"editTypes_set = set(['substitution', 'insertion', 'deletion'])\n",
"# propose what do you want the target modified transcript to be\n",
"target_transcript = \"But when I saw the mirage of the lake in the distance, which the sense deceives, Lost not by distance any of its marks,\"\n",
"edit_type = \"substitution\"\n",
"assert edit_type in editTypes_set, f\"Invalid edit type {edit_type}. Must be one of {editTypes_set}.\"\n",
"\n",
"# if you want to do a second modification on top of the first one, write down the second modification (target_transcript2, type_of_modification2)\n",
"# make sure the two modification do not overlap, if they do, you need to combine them into one modification\n",
"\n",
"# run the script to turn user input to the format that the model can take\n",
"from edit_utils import get_span\n",
"orig_span, new_span = get_span(orig_transcript, target_transcript, edit_type)\n",
"if orig_span[0] > orig_span[1]:\n",
" RuntimeError(f\"example {audio_fn} failed\")\n",
"if orig_span[0] == orig_span[1]:\n",
" orig_span_save = [orig_span[0]]\n",
"else:\n",
" orig_span_save = orig_span\n",
"if new_span[0] == new_span[1]:\n",
" new_span_save = [new_span[0]]\n",
"else:\n",
" new_span_save = new_span\n",
"\n",
"orig_span_save = \",\".join([str(item) for item in orig_span_save])\n",
"new_span_save = \",\".join([str(item) for item in new_span_save])\n",
"from inference_speech_editing_scale import get_mask_interval\n",
"\n",
"start, end = get_mask_interval(align_fn, orig_span_save, edit_type)\n",
"info = torchaudio.info(audio_fn)\n",
"audio_dur = info.num_frames / info.sample_rate\n",
"morphed_span = (max(start - left_margin, 1/codec_sr), min(end + right_margin, audio_dur)) # in seconds\n",
"\n",
"# span in codec frames\n",
"mask_interval = [[round(morphed_span[0]*codec_sr), round(morphed_span[1]*codec_sr)]]\n",
"mask_interval = torch.LongTensor(mask_interval) # [M,2], M==1 for now\n",
"\n",
"# load model, tokenizer, and other necessary files\n",
"ckpt_fn = \"/data/scratch/pyp/exp_pyp/VoiceCraft/gigaspeech/pretrained_830M/best_bundle.pth\"\n",
"encodec_fn = \"/data/scratch/pyp/exp_pyp/audiocraft/encodec/xps/6f79c6a8/checkpoint.th\"\n",
"ckpt = torch.load(ckpt_fn, map_location=\"cpu\")\n",
"model = voicecraft.VoiceCraft(ckpt[\"config\"])\n",
"model.load_state_dict(ckpt[\"model\"])\n",
"model.to(device)\n",
"model.eval()\n",
"\n",
"phn2num = ckpt['phn2num']\n",
"\n",
"text_tokenizer = TextTokenizer(backend=\"espeak\")\n",
"audio_tokenizer = AudioTokenizer(signature=encodec_fn) # will also put the neural codec model on gpu\n",
"\n",
"# run the model to get the output\n",
"from inference_speech_editing_scale import inference_one_sample\n",
"\n",
"decode_config = {'top_k': top_k, 'top_p': top_p, 'temperature': temperature, 'stop_repetition': stop_repetition, 'kvcache': kvcache, \"codec_audio_sr\": codec_audio_sr, \"codec_sr\": codec_sr, \"silence_tokens\": silence_tokens}\n",
"orig_audio, new_audio = inference_one_sample(model, ckpt[\"config\"], phn2num, text_tokenizer, audio_tokenizer, audio_fn, target_transcript, mask_interval, device, decode_config)\n",
" \n",
"# save segments for comparison\n",
"orig_audio, new_audio = orig_audio[0].cpu(), new_audio[0].cpu()\n",
"# logging.info(f\"length of the resynthesize orig audio: {orig_audio.shape}\")\n",
"\n",
"# output_dir\n",
"output_dir = \"./demo/generated_se\"\n",
"os.makedirs(output_dir, exist_ok=True)\n",
"\n",
"save_fn_new = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_new_seed{seed}.wav\"\n",
"\n",
"torchaudio.save(save_fn_new, new_audio, codec_audio_sr)\n",
"\n",
"save_fn_orig = f\"{output_dir}/{os.path.basename(audio_fn)[:-4]}_orig.wav\"\n",
"if not os.path.isfile(save_fn_orig):\n",
" orig_audio, orig_sr = torchaudio.load(audio_fn)\n",
" if orig_sr != codec_audio_sr:\n",
" orig_audio = torchaudio.transforms.Resample(orig_sr, codec_audio_sr)(orig_audio)\n",
" torchaudio.save(save_fn_orig, orig_audio, codec_audio_sr)\n",
"\n",
"# if you get error importing T5 in transformers\n",
"# try \n",
"# pip uninstall Pillow\n",
"# pip install Pillow\n",
"# you are likely to get warning looks like WARNING:phonemizer:words count mismatch on 300.0% of the lines (3/1), this can be safely ignored"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "voicecraft",
"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": "3.9.18"
}
},
"nbformat": 4,
"nbformat_minor": 2
}