wav2vec phonemes
Incomplete, Irish
• 6 min read
from datasets import load_dataset
dirs = """
cmg_ga_mu_corpusbeag
pmg_ga_co/RCPiarsachALL
nnc_ga_mu/CDNamedEntities01
nnc_ga_mu/CDAn_tOileanach_part3_newLTS
nnc_ga_mu/CDAn_tOileanach_part4_newLTS
nnc_ga_mu/CDNamedEntities02
nnc_ga_mu/CDAlphabet
nnc_ga_mu/CDAn_tOileanach_part2_newLTS
nnc_ga_mu/corpas_beag_newLTS
nnc_ga_mu/CDSaytime
nnc_ga_mu/CDAn_tOileanach_part1_newLTS
cmg_ga_mu/CMGOther
cmg_ga_mu/CMGCorpusBeag
anb_ga_ul/new_text02
anb_ga_ul/text01-004
anb_ga_ul/text01
anb_ga_ul/text01-001
anb_ga_ul/text02
anb_ga_ul/named-entities
nnc_en_ie
"""
dirl = [a for a in dirs.split("\n") if a]
script = "abairxml.py"
test = load_dataset(script, data_dir="/home/jim/tmp/cmg_ga_mu/CMGOther")
Using custom data configuration default-3a69a91aa0b88fa1 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b)
test
DatasetDict({
train: Dataset({
features: ['file_id', 'words', 'phonemes', 'audio', 'dialect', 'language', 'speaker_id', 'audio_set'],
num_rows: 737
})
})
test['train'][0]
{'file_id': 'CI0002CMGNamedEntities01_0202',
'words': 'gaeilge na halban',
'phonemes': ['g',
'ee',
'lj',
'gj',
'@',
'n',
'@',
'h',
'a',
'l',
'@',
'b',
'@',
'n'],
'audio': '/home/jim/tmp/cmg_ga_mu/CMGOther/wav16_trimmed/CI0002CMGNamedEntities01_0202.wav',
'dialect': 'mu',
'language': 'ga',
'speaker_id': 'cmg',
'audio_set': 'CMGOther'}
from pathlib import Path
def check_paths(batch):
audio_path = Path(batch["audio"])
return audio_path.is_file()
test.filter(check_paths)
Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-fd1748b2b209eed2.arrow
DatasetDict({
train: Dataset({
features: ['file_id', 'words', 'phonemes', 'audio', 'dialect', 'language', 'speaker_id', 'audio_set'],
num_rows: 737
})
})
sets = {}
for dir in dirl:
sets[dir] = load_dataset(script, data_dir=f"/home/jim/tmp/{dir}")
Using custom data configuration default-187ee4831f664a6d Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-aa8abe91265ea5f3 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-7667bb9aedbb818e Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-7a61ec2b352637f4 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-da3752ae2db10e54 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-bc83211c090696b1 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-8a5c6623ef11cf95 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-8898f01d8441980f Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-f3018c93372fbb3e Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-394fefcb2267b139 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-e19a455adb1dd118 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-3a69a91aa0b88fa1 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-be79e07535743a6e Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-417c6e27426f3437 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-43028c0e5f2c58ca Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-a06c04423430a170 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-47dd039cf717a18f Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-157f875646b8e11f Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-5889ff1f5cce90e0 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b) Using custom data configuration default-336db2235fd49907 Reusing dataset utterance_xml_dataset (/home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b)
from pathlib import Path
def check_paths(batch):
audio_path = Path(batch["audio"])
return audio_path.is_file()
for dir in dirl:
sets[dir]["train"] = sets[dir]["train"].filter(check_paths)
Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-96d34247636a824d.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7018f164471d5b99.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-4ae746a5bb8ab867.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-65a1ed1f06c66730.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-f85df38cd0c18760.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-a78531c403493484.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-9ac80223370644e8.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-8ba453ba495337c2.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-f4d3a1c2d91a3cbc.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-6bbe18519e4dc0d0.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-884ba0c370db2771.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-fd1748b2b209eed2.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-b0de8317eeb157fe.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-4ec6f50627536c4a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-25508f353dffe5a4.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-6b89d3ce1380a94e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-eaa23f6d212ea43c.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-d43c63ec8d4cb897.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3347d4b8bca7b86e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-84a411d0343a3512.arrow
!pip install torchaudio
Keyring is skipped due to an exception: Item does not exist! Defaulting to user installation because normal site-packages is not writeable Requirement already satisfied: torchaudio in /home/jim/.local/lib/python3.6/site-packages (0.9.0) Requirement already satisfied: torch==1.9.0 in /home/jim/.local/lib/python3.6/site-packages (from torchaudio) (1.9.0) Requirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from torch==1.9.0->torchaudio) (0.8) Requirement already satisfied: typing-extensions in /usr/local/lib/python3.6/dist-packages (from torch==1.9.0->torchaudio) (3.7.4.3)
import torchaudio
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch["audio"])
batch["speech"] = speech_array[0].numpy()
batch["sampling_rate"] = sampling_rate
batch["target_text"] = batch["words"]
return batch
for dir in dirl:
sets[dir]["train"] = sets[dir]["train"].map(speech_file_to_array_fn, remove_columns=sets[dir]["train"].column_names)
Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-18df1d089931c98b.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-0eaad84bca78a073.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3c31f68123fd7809.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-57b4fd0b447303a2.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-73c2eff8b5378aab.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-da5ca26a2d03ecdc.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-2a1a8dd5ed530678.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-aaf3b67f0e27c4a6.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-2af0e4d1625ddf67.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ea40fec907410ed4.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7398224424cce64c.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7c7e8160e8406935.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ae73b888f9fe20f5.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-a9963450e3885f8e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-b76ed6fa3fb8afe1.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-bbb66523817ad4df.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ca76c6c18b4abf91.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-1af7e68fe08b5207.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ff6b9124b076f8e5.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-14f81baac928b43a.arrow
Something has gone wrong with anb_ga_ul/text02
Audio is in wav_trimmed/
import librosa
import numpy as np
def resample(batch):
batch["duration"] = librosa.get_duration(y=batch["speech"], sr=batch["sampling_rate"])
if batch["sampling_rate"] != 16_000:
batch["speech"] = librosa.resample(np.asarray(batch["speech"]), batch["sampling_rate"], 16_000)
batch["sampling_rate"] = 16_000
return batch
for dir in dirl:
sets[dir]["train"] = sets[dir]["train"].map(resample, num_proc=4)
Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-da006be1caebfb5b.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-c2641d558f05e8f1.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-8d515b7aebd171c2.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-187ee4831f664a6d/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7b97b92998e9a71e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-b930ee8e08c75d17.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-16fc7e0af6cdfbfe.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3e197422dcab423a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-aa8abe91265ea5f3/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-0bbffbb7006c1760.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ddf707dfe4b7d23d.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7945f9aa2bbe78be.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-aa80776b825505d5.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7667bb9aedbb818e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3f20a852f448150e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-020554618c0473da.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-80c4a8247db8a5f0.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3faf7bd55f7b23b8.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-7a61ec2b352637f4/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-f0ae75f51af33439.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-04a363fa350e2d0e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-2abb738d8bc4459c.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3cdfa94b1df3c632.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-da3752ae2db10e54/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-0fc4b55b3a4a2747.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ea4959f2bba4dea2.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-900f99bfe0821493.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-ccf6b5fa58f6adc9.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-bc83211c090696b1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-6b04de2ba84f5c1e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-cbe5a0628979048a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-e13656197518a3f6.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-177a6afeba2748dc.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8a5c6623ef11cf95/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-95436c45266b6c27.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-af5bb7875287b69a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-00a080c84b760bd7.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-4afdde4b44ec1887.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-8898f01d8441980f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-99504b4627c17479.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-b30d932595452bbc.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-fa12130562cc624b.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-37d2947aed3d9622.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-f3018c93372fbb3e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-34ddde6cc95cac6a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-dcded5d4eedfd04d.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-bd1b787e7a143ed9.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-bb045d0847c313cf.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-394fefcb2267b139/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-fcb22388e1a65bcb.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-83fd8971f21f0642.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-4b82451aaabf6f8a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-224175b2f73773b6.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-e19a455adb1dd118/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-4ad7b01211873d7f.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-b7a0c5aa39c78ae6.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-27eecbb93ff48548.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-c6ab1d3a70bb51dd.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-3a69a91aa0b88fa1/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3b74a87459f4bb04.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-5f5e02953a0c6c6b.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-8587b9046b2a82a2.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-376ba06e76353015.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-be79e07535743a6e/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7d11fe2d6553624f.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-a4be9ba595044bad.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-427ef18cc67eebae.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-99c6205ccc49b25c.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-417c6e27426f3437/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-e7f0518821b0b9e6.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-e0c7add3e9eea943.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-9e455766f23deb5c.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-2a43a708bcd6125b.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-43028c0e5f2c58ca/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-e4d637a438294fc6.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-97a05d3db37ee5cd.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-c1c7825e1bc02b5a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-465919010ff30a72.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-a06c04423430a170/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-c64d38a0849d0bc5.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-58500e78ee38aaea.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-b36050bc7f2ec07b.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-c268deaf2f939914.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-47dd039cf717a18f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-edcdf3391c08e5da.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-24c570fcca1b464c.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-9f75694b34c4f231.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-071b3ece1c6a120d.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-157f875646b8e11f/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-fd2a4a2145768b59.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-5c2fb0a2f108d581.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-57b57bae7ef6f535.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-02dc0c3842a1ad9e.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-5889ff1f5cce90e0/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-3f5ba5d5a78eb5ca.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-881af4492aebe81a.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7aedf943d48feded.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-6f33f192208438a7.arrow Loading cached processed dataset at /home/jim/.cache/huggingface/datasets/utterance_xml_dataset/default-336db2235fd49907/1.1.0/2ab4d5a39b76b2b213d176be1f94b8bb2c34198ea2fabf4b281e0784782b2d2b/cache-7ca896c968beb535.arrow