Fleurs (lhotse-speech#1402)

* Adds fleurs recipe

* Black formatting

* Removes useless num_jobs argument in the download cli, and ran isort and black again on *recipes/fleurs.py

* Removes what appears to be an unnecessary set_ffmpeg_torchaudio_info call

* isort and black fix

* Fixes remaining black issues due to trailing space in recipes/__init__.py

* Adds FLEURS entry in docs/corpus.rst

docs/corpus.rst

@@ -109,6 +109,8 @@ a CLI tool that create the manifests given a corpus directory.
     - :func:`lhotse.recipes.prepare_fisher_english`
   * - Fisher Spanish
     - :func:`lhotse.recipes.prepare_fisher_spanish`
+  * - FLEURS
+    - :func:`lhotse.recipes.prepare_fleurs`
   * - Fluent Speech Commands
     - :func:`lhotse.recipes.slu`
   * - GALE Arabic Broadcast Speech

lhotse/bin/modes/recipes/__init__.py

@@ -34,6 +34,7 @@
 from .eval2000 import *
 from .fisher_english import *
 from .fisher_spanish import *
+from .fleurs import *
 from .gale_arabic import *
 from .gale_mandarin import *
 from .gigaspeech import *

lhotse/bin/modes/recipes/fleurs.py

@@ -0,0 +1,68 @@
+from typing import Optional, Sequence, Union
+
+import click
+
+from lhotse.bin.modes import download, prepare
+from lhotse.recipes.fleurs import download_fleurs, prepare_fleurs
+from lhotse.utils import Pathlike
+
+__all__ = ["fleurs"]
+
+
+@prepare.command(context_settings=dict(show_default=True))
+@click.argument("corpus_dir", type=click.Path(exists=True, dir_okay=True))
+@click.argument("output_dir", type=click.Path())
+@click.option(
+    "-j",
+    "--num-jobs",
+    type=int,
+    default=1,
+    help="How many threads to use (can give good speed-ups with slow disks).",
+)
+@click.option(
+    "-l",
+    "--lang",
+    multiple=True,
+    default=["all"],
+    help="Specify which languages to prepare, e.g., "
+    "        lhoste prepare librispeech mtedx_corpus data -l de -l fr -l es ",
+)
+def fleurs(
+    corpus_dir: Pathlike,
+    output_dir: Pathlike,
+    num_jobs: int,
+    lang: Optional[Union[str, Sequence[str]]],
+):
+    """Fleurs ASR data preparation."""
+    prepare_fleurs(corpus_dir, output_dir=output_dir, num_jobs=num_jobs, languages=lang)
+
+
+@download.command(context_settings=dict(show_default=True))
+@click.argument("target_dir", type=click.Path())
+@click.option(
+    "-l",
+    "--lang",
+    multiple=True,
+    default=["all"],
+    help="Specify which languages to download, e.g., "
+    "        lhotse download fleurs . -l hi_in -l en_us "
+    "        lhotse download fleurs",
+)
+@click.option(
+    "--force-download",
+    type=bool,
+    is_flag=True,
+    default=False,
+    help="Specify whether to overwrite an existing archive",
+)
+def fleurs(
+    target_dir: Pathlike,
+    lang: Optional[Union[str, Sequence[str]]],
+    force_download: bool = False,
+):
+    """FLEURS download."""
+    download_fleurs(
+        target_dir,
+        languages=lang,
+        force_download=force_download,
+    )

lhotse/recipes/__init__.py

@@ -31,6 +31,7 @@
 from .eval2000 import prepare_eval2000
 from .fisher_english import prepare_fisher_english
 from .fisher_spanish import prepare_fisher_spanish
+from .fleurs import download_fleurs, prepare_fleurs
 from .gale_arabic import prepare_gale_arabic
 from .gale_mandarin import prepare_gale_mandarin
 from .gigaspeech import prepare_gigaspeech
@@ -147,6 +148,8 @@
     "prepare_eval2000",
     "prepare_fisher_english",
     "prepare_fisher_spanish",
+    "download_fleurs",
+    "prepare_fleurs",
     "prepare_gale_arabic",
     "prepare_gale_mandarin",
     "prepare_gigaspeech",