sahishnu / fairseq_meta_mms_google_colab_implementation Goto Github PK

import os

!git clone https://github.com/pytorch/fairseq

# Get the current working directory
current_dir = os.getcwd()

# Create the directory paths
audio_samples_dir = os.path.join(current_dir, "audio_samples")
temp_dir = os.path.join(current_dir, "temp_dir")

# Create the directories if they don't exist
os.makedirs(audio_samples_dir, exist_ok=True)
os.makedirs(temp_dir, exist_ok=True)


# Change current working directory
os.chdir('fairseq')

!pwd

# # MMS-1B:FL102 model - 102 Languages - FLEURS Dataset
# !wget -P ./models_new 'https://dl.fbaipublicfiles.com/mms/asr/mms1b_fl102.pt'

# # MMS-1B:L1107 - 1107 Languages - MMS-lab Dataset
# !wget -P ./models_new 'https://dl.fbaipublicfiles.com/mms/asr/mms1b_l1107.pt'

# MMS-1B-all - 1162 Languages - MMS-lab + FLEURS + CV + VP + MLS
!wget -P ./models_new 'https://dl.fbaipublicfiles.com/mms/asr/mms1b_all.pt'

ffmpeg -i .\small_trim4.mp3 -ar 16000 .\wav_formats\small_trim4.wav

import os

os.environ["TMPDIR"] = '/content/temp_dir'
os.environ["PYTHONPATH"] = "."
os.environ["PREFIX"] = "INFER"
os.environ["HYDRA_FULL_ERROR"] = "1"
os.environ["USER"] = "micro"

!python examples/mms/asr/infer/mms_infer.py --model "/content/fairseq/models_new/mms1b_all.pt" --lang "swh" --audio "/content/audio_samples/small_trim4.wav"