move to earnings instead of earnings21

Signed-off-by: Nithin Rao Koluguri <nithinrao.koluguri@gmail.com>

Author: nithinraok

…t_configs/english/earnings21/config.yaml …set_configs/english/earnings/config.yamldataset_configs/english/earnings21/config.yaml renamed to dataset_configs/english/earnings/config.yaml dataset_configs/english/earnings21/config.yaml renamed to dataset_configs/english/earnings/config.yaml

@@ -134,7 +134,7 @@ documentation: |
   
   .. code-block:: bash
 
-    python main.py --config-path=dataset_configs/english/earnings21 --config-name=config \
+    python main.py --config-path=dataset_configs/english/earnings --config-name=config \
       dataset_type=earnings21 \
       dataset_root=/path/to/earnings21 \
       output_directory=/path/to/output
@@ -143,7 +143,7 @@ documentation: |
   
   .. code-block:: bash
 
-    python main.py --config-path=dataset_configs/english/earnings21 --config-name=config \
+    python main.py --config-path=dataset_configs/english/earnings --config-name=config \
       dataset_type=earnings22 \
       forced_alignment_model=nvidia/parakeet-tdt_ctc-1.1b \
       dataset_root=/path/to/earnings22 \
@@ -153,7 +153,7 @@ documentation: |
   
   .. code-block:: bash
 
-    python main.py --config-path=dataset_configs/english/earnings21 --config-name=config \
+    python main.py --config-path=dataset_configs/english/earnings --config-name=config \
       dataset_type=earnings21 \
       subset=eval10 \
       dataset_root=/path/to/earnings21 \
@@ -193,7 +193,7 @@ forced_alignment_model: nvidia/parakeet-tdt_ctc-1.1b
 device: "cuda"
 
 processors:
-  - _target_: sdp.processors.datasets.earnings21.CreateInitialAudioAndManifest
+  - _target_: sdp.processors.datasets.earnings.CreateInitialAudioAndManifest
     dataset_root: ${dataset_root}
     raw_audio_source_dir: ${raw_audio_input_dir}
     output_manifest_file: ${output_directory}/01_initial_audio_manifest.json
@@ -211,7 +211,7 @@ processors:
     target_samplerate: 16000
     target_nchannels: 1
 
-  - _target_: sdp.processors.datasets.earnings21.CreateFullAudioManifestEarnings21
+  - _target_: sdp.processors.datasets.earnings.CreateFullAudioManifestEarnings21
     input_manifest_file: ${output_directory}/02_converted_audio_manifest.json
     dataset_root: ${dataset_root}
     output_manifest_file: ${output_directory}/03_full_audio_with_text_manifest.json
@@ -227,20 +227,20 @@ processors:
       - {"pattern": "<.*?>", "repl": ""}
       - {"pattern": "\\[.*?\\]", "repl": ""}
 
-  - _target_: sdp.processors.datasets.earnings21.NeMoForcedAligner
+  - _target_: sdp.processors.datasets.earnings.NeMoForcedAligner
     input_manifest_file: ${output_directory}/04_full_audio_with_text_manifest_cleaned.json
     output_manifest_file: ${output_directory}/05_aligned_manifest.json
     output_dir: ${output_directory}/forced_alignment_output
     pretrained_name: ${forced_alignment_model}
     device: ${device}
     batch_size: 1
 
-  - _target_: sdp.processors.datasets.earnings21.CreateSentenceSegmentedManifest
+  - _target_: sdp.processors.datasets.earnings.CreateSentenceSegmentedManifest
     input_manifest_file: ${output_directory}/05_aligned_manifest.json
     ctm_dir: ${output_directory}/forced_alignment_output/ctm/words
     output_manifest_file: ${output_directory}/06_sentence_segmented_manifest.json
 
-  - _target_: sdp.processors.datasets.earnings21.SpeakerSegmentedManifest
+  - _target_: sdp.processors.datasets.earnings.SpeakerSegmentedManifest
     input_manifest_file: ${output_directory}/04_full_audio_with_text_manifest_cleaned.json
     dataset_root: ${dataset_root}
     output_manifest_file: ${output_directory}/07_speaker_segmented_manifest.json

sdp/processors/__init__.py

@@ -21,7 +21,7 @@
     CreateInitialManifestCORAAL,
     TrainDevTestSplitCORAAL,
 )
-from sdp.processors.datasets.earnings21 import (
+from sdp.processors.datasets.earnings import (
     CreateInitialAudioAndManifest,
     CreateFullAudioManifestEarnings21,
     SpeakerSegmentedManifest,

…ocessors/datasets/earnings21/__init__.py …processors/datasets/earnings/__init__.pysdp/processors/datasets/earnings21/__init__.py renamed to sdp/processors/datasets/earnings/__init__.py sdp/processors/datasets/earnings21/__init__.py renamed to sdp/processors/datasets/earnings/__init__.py

@@ -12,13 +12,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from sdp.processors.datasets.earnings21.create_initial_manifest import (
+from sdp.processors.datasets.earnings.create_initial_manifest import (
     CreateInitialAudioAndManifest,
     CreateFullAudioManifestEarnings21,
     SpeakerSegmentedManifest,
     CreateSentenceSegmentedManifest,
     NeMoForcedAligner,
 )
-from sdp.processors.datasets.earnings21.apply_normalizations import (
+from sdp.processors.datasets.earnings.apply_normalizations import (
     ApplyEarnings21Normalizations,
 ) 

…asets/earnings21/apply_normalizations.py …atasets/earnings/apply_normalizations.pysdp/processors/datasets/earnings21/apply_normalizations.py renamed to sdp/processors/datasets/earnings/apply_normalizations.py sdp/processors/datasets/earnings21/apply_normalizations.py renamed to sdp/processors/datasets/earnings/apply_normalizations.py

@@ -38,7 +38,7 @@ class ApplyEarnings21Normalizations(BaseProcessor):
     Example:
         .. code-block:: yaml
 
-            - _target_: sdp.processors.datasets.earnings21.ApplyEarnings21Normalizations
+            - _target_: sdp.processors.datasets.earnings.ApplyEarnings21Normalizations
               earnings21_root: /path/to/earnings21
               use_top_candidate: true
               fallback_to_original: true

…ts/earnings21/create_initial_manifest.py …sets/earnings/create_initial_manifest.pysdp/processors/datasets/earnings21/create_initial_manifest.py renamed to sdp/processors/datasets/earnings/create_initial_manifest.py sdp/processors/datasets/earnings21/create_initial_manifest.py renamed to sdp/processors/datasets/earnings/create_initial_manifest.py

@@ -50,7 +50,7 @@ class CreateInitialAudioAndManifest(BaseParallelProcessor):
     Example:
         .. code-block:: yaml
 
-            - _target_: sdp.processors.datasets.earnings21.CreateInitialAudioAndManifest
+            - _target_: sdp.processors.datasets.earnings.CreateInitialAudioAndManifest
               dataset_root: /path/to/earnings21
               raw_audio_source_dir: ${dataset_root}/media
               output_manifest_file: ${output_dir}/01_initial_manifest.json
@@ -181,7 +181,7 @@ class CreateFullAudioManifestEarnings21(BaseParallelProcessor):
     Example:
         .. code-block:: yaml
 
-            - _target_: sdp.processors.datasets.earnings21.CreateFullAudioManifestEarnings21
+            - _target_: sdp.processors.datasets.earnings.CreateFullAudioManifestEarnings21
               input_manifest_file: ${output_dir}/01_initial_manifest.json
               dataset_root: /path/to/earnings21
               output_manifest_file: ${output_dir}/02_manifest_with_text.json
@@ -334,7 +334,7 @@ class SpeakerSegmentedManifest(BaseParallelProcessor):
     Example:
         .. code-block:: yaml
 
-            - _target_: sdp.processors.datasets.earnings21.SpeakerSegmentedManifest
+            - _target_: sdp.processors.datasets.earnings.SpeakerSegmentedManifest
               input_manifest_file: ${output_dir}/02_manifest_with_text.json
               dataset_root: /path/to/earnings21
               output_manifest_file: ${output_dir}/06_speaker_segments.json
@@ -627,7 +627,7 @@ class CreateSentenceSegmentedManifest(BaseParallelProcessor):
     Example:
         .. code-block:: yaml
 
-            - _target_: sdp.processors.datasets.earnings21.CreateSentenceSegmentedManifest
+            - _target_: sdp.processors.datasets.earnings.CreateSentenceSegmentedManifest
               input_manifest_file: ${output_dir}/04_aligned_manifest.json
               ctm_dir: ${output_dir}/forced_alignment_output/ctm/words
               output_manifest_file: ${output_dir}/05_sentence_segments.json
@@ -839,7 +839,7 @@ class NeMoForcedAligner(BaseProcessor):
     Example:
         .. code-block:: yaml
 
-            - _target_: sdp.processors.datasets.earnings21.NeMoForcedAligner
+            - _target_: sdp.processors.datasets.earnings.NeMoForcedAligner
               input_manifest_file: ${output_dir}/03_cleaned_manifest.json
               output_manifest_file: ${output_dir}/04_aligned_manifest.json
               output_dir: ${output_dir}/forced_alignment_output