Skip to content

Provide dir path not xml file for whisper pipline #4008

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pwolnows merged 1 commit into from
Apr 9, 2025
Merged

Provide dir path not xml file for whisper pipline #4008

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions tools/accuracy_checker/accuracy_checker/evaluators/custom_evaluators/whisper_evaluator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
limitations under the License.
"""
import re
import os

from ...representation import CharacterRecognitionPrediction
from ...utils import UnsupportedPackage, extract_image_representations
Expand Down Expand Up @@ -121,7 +122,7 @@ def _initialize_pipeline(self, config):
except ImportError as import_error:
UnsupportedPackage("openvino_genai", import_error.msg).raise_error(self.__class__.__name__)

model_dir = config.get("_models", [None])[0]
model_dir = get_model_dir(config)
device = config.get("_device", "CPU")
pipeline = ov_genai.WhisperPipeline(str(model_dir), device=device)
return pipeline
Expand Down Expand Up @@ -169,7 +170,7 @@ def _initialize_pipeline(self, config):
UnsupportedPackage("optimum.intel.openvino", import_error.msg).raise_error(self.__class__.__name__)

device = config.get("_device", "CPU")
model_dir = config.get("_models", [None])[0]
model_dir = get_model_dir(config)
ov_model = OVModelForSpeechSeq2Seq.from_pretrained(str(model_dir)).to(device)
ov_processor = AutoProcessor.from_pretrained(str(model_dir))

Expand All @@ -184,3 +185,12 @@ def _get_predictions(self, data, identifiers, input_meta):
sampling_rate = input_meta[0].get("sample_rate")
sample = {"path": identifiers[0], "array": data[0], "sampling_rate": sampling_rate}
return self.pipeline(sample, return_timestamps=True)["text"]



def get_model_dir(config):
model_path = config.get("_models", [None])[0]

if os.path.isfile(model_path):
return os.path.dirname(model_path)
return model_path
Loading