shichen.fsc e134254c6c [to #42322933] add foreign language supported, and audio data resample -- asr inference ...

asr推理增加对其他外文的支持，包括计算wer。
增加对音频重采样，根据传入音频的采样率和当前模型支持的采样率，在easyasr内部完成重采样。注意，输入数据为pcm时，需要同时传入pcm的sample rate，否则当成16K。
        Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/9580609

2022-08-02 21:52:39 +08:00

..

__init__.py

[to #41401401] add preprocessor, model and pipeline

2022-05-19 22:18:35 +08:00

test_action_recognition.py

[to #42322933] support text to image synthesis default model

2022-07-04 14:21:22 +08:00

test_animal_recognation.py

[to #42322933]formalize test data storage

2022-07-04 12:11:12 +08:00

test_automatic_speech_recognition.py

[to #42322933] add foreign language supported, and audio data resample -- asr inference

2022-08-02 21:52:39 +08:00

test_base.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_builder.py

[to #43112692] stardarized task name and output

2022-08-02 20:21:05 +08:00

test_cmdssl_video_embedding.py

[to #42322933] Add cv_r2p1d_video_embedding to maas lib

2022-07-04 16:05:52 +08:00

test_csanmt_translation.py

[to #43115042] add trainer usage doc

2022-07-29 10:28:50 +08:00

test_dialog_intent_prediction.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_dialog_modeling.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_dialog_state_tracking.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_face_detection.py

[to #42322933]add cv-faceDetection and cv-faceRecognition

2022-07-28 21:52:18 +08:00

test_face_image_generation.py

[to #42322933] Update tasks of face_image_generation and image_super_resolution

2022-07-21 18:17:25 +08:00

test_face_recognition.py

[to #42322933]add cv-faceDetection and cv-faceRecognition

2022-07-28 21:52:18 +08:00

test_fill_mask.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_general_image_classification.py

[to #42322933] Add image-classification-imagenet and image-classification-dailylife pipelines

2022-07-27 22:29:13 +08:00

test_generative_multi_modal_embedding.py

[to #42322933] add generative multimodal embedding model

2022-07-26 14:09:18 +08:00

test_image2image_generation.py

upload image_to_image_generation code

2022-08-02 00:04:26 +08:00

test_image2image_translation.py

[to #43112692] stardarized task name and output

2022-08-02 20:21:05 +08:00

test_image_color_enhance.py

[to #43112692] stardarized task name and output

2022-08-02 20:21:05 +08:00

test_image_colorization.py

[to #42322933] Add image--pipeline to maas lib

2022-07-22 10:29:38 +08:00

test_image_denoise.py

[to #43112692] stardarized task name and output

2022-08-02 20:21:05 +08:00

test_image_instance_segmentation.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_image_matting.py

[to #43112692] stardarized task name and output

2022-08-02 20:21:05 +08:00

test_image_portrait_enhancement.py

[to #42322933]人像增强

2022-08-02 21:33:32 +08:00

test_image_style_transfer.py

[to #42322933]Merge request from 雪洛:rename-style-transfer

2022-08-02 11:01:09 +08:00

test_image_super_resolution.py

[to #42322933] Update tasks of face_image_generation and image_super_resolution

2022-07-21 18:17:25 +08:00

test_key_word_spotting.py

[to #42322933] simplify kws code, and remove disk-write behavior

2022-07-25 22:37:15 +08:00

test_live_category.py

[to #42322933]add cv_resnet50_live-category

2022-07-28 10:07:33 +08:00

test_multi_modal_embedding.py

[to #42322933]add multi-modal-feature

2022-06-27 11:57:22 +08:00

test_named_entity_recognition.py

[to #42322933] disable ner test temporarily

2022-08-01 13:35:16 +08:00

test_nli.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_object_detection.py

[to #42322933] update detection task name

2022-08-02 12:02:31 +08:00

test_ocr_detection.py

[to #42322933]Merge branch 'master' into ocr/ocr_detection

2022-06-28 14:03:01 +08:00

test_ofa_tasks.py

[to #42322933] add init and make demo compatible link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/9606656

2022-08-02 20:42:13 +08:00

test_person_image_cartoon.py

[to #42322933] rename task of person_image_cartoon and fix a bug

2022-08-02 13:09:49 +08:00

test_product_retrieval_embedding.py

[to #42322933]Merge request from 仲理:feat/product_feature

2022-08-01 17:53:22 +08:00

test_sentence_similarity.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_sentiment_classification.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_speech_signal_process.py

[to #42322933] feat: aec pipeline also accept tuple and add test

2022-08-02 14:03:11 +08:00

test_text_classification.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_text_error_correction.py

[to #42322933][NLP] Add text error correction task

2022-07-28 23:01:28 +08:00

test_text_generation.py

[to #42322933] Add GPT3 base model

2022-07-30 11:03:01 +08:00

test_text_to_image_synthesis.py

[to #43112534] finetune support and first case

2022-07-14 16:25:55 +08:00

test_text_to_speech.py

[to #42322933] Update tts task inputs

2022-07-18 17:50:59 +08:00

test_video_category.py

[to #42322933] add cv_resnet50_video-category to maas lib

2022-07-27 23:42:27 +08:00

test_video_multi_modal_embedding.py

[to #42322933]add video multi-model feature

2022-07-26 22:48:07 +08:00

test_virtual_try_on.py

[to #43133921] change name(virtual-tryon to virtual-try-on)

2022-08-02 14:36:44 +08:00

test_visual_question_answering.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_word_segmentation.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00

test_zero_shot_classification.py

[to #43112771] requirements check and lazy import support

2022-07-27 17:29:16 +08:00