Python
- ctranslate2
- AsyncGenerationResult
- AsyncScoringResult
- AsyncTranslationResult
- DataType
- Device
- Encoder
- EncoderForwardOutput
- ExecutionStats
- GenerationResult
- GenerationStepResult
- Generator
GeneratorGenerator.__init__()Generator.async_generate_tokens()Generator.forward_batch()Generator.generate_batch()Generator.generate_iterable()Generator.generate_tokens()Generator.load_model()Generator.score_batch()Generator.score_iterable()Generator.unload_model()Generator.compute_typeGenerator.deviceGenerator.device_indexGenerator.model_is_loadedGenerator.num_active_batchesGenerator.num_generatorsGenerator.num_queued_batchesGenerator.tensor_parallel
- MpiInfo
- ScoringResult
- StorageView
- TranslationResult
- Translator
TranslatorTranslator.__init__()Translator.generate_tokens()Translator.load_model()Translator.score_batch()Translator.score_file()Translator.score_iterable()Translator.translate_batch()Translator.translate_file()Translator.translate_iterable()Translator.unload_model()Translator.compute_typeTranslator.deviceTranslator.device_indexTranslator.model_is_loadedTranslator.num_active_batchesTranslator.num_queued_batchesTranslator.num_translatorsTranslator.tensor_parallel
- contains_model
- get_cuda_device_count
- get_log_level
- get_supported_compute_types
- set_log_level
- set_random_seed
- ctranslate2.converters
- ctranslate2.models
- Wav2Vec2
- Wav2Vec2Bert
Wav2Vec2BertWav2Vec2Bert.__init__()Wav2Vec2Bert.encode()Wav2Vec2Bert.load_model()Wav2Vec2Bert.unload_model()Wav2Vec2Bert.compute_typeWav2Vec2Bert.deviceWav2Vec2Bert.device_indexWav2Vec2Bert.model_is_loadedWav2Vec2Bert.num_active_batchesWav2Vec2Bert.num_queued_batchesWav2Vec2Bert.num_workersWav2Vec2Bert.tensor_parallel
- Whisper
WhisperWhisper.__init__()Whisper.align()Whisper.detect_language()Whisper.encode()Whisper.generate()Whisper.load_model()Whisper.unload_model()Whisper.compute_typeWhisper.deviceWhisper.device_indexWhisper.is_multilingualWhisper.model_is_loadedWhisper.n_melsWhisper.num_active_batchesWhisper.num_languagesWhisper.num_queued_batchesWhisper.num_workersWhisper.tensor_parallel
- WhisperGenerationResult
- WhisperGenerationResultAsync
- ctranslate2.specs
- Activation
- EmbeddingsMerge
- LanguageModelSpec
LanguageModelSpecLanguageModelSpec.__init__()LanguageModelSpec.get_default_config()LanguageModelSpec.get_vocabulary_size()LanguageModelSpec.optimize()LanguageModelSpec.register_file()LanguageModelSpec.register_vocabulary()LanguageModelSpec.save()LanguageModelSpec.validate()LanguageModelSpec.variables()LanguageModelSpec.configLanguageModelSpec.nameLanguageModelSpec.revision
- LayerSpec
- ModelSpec
- RotaryScalingType
- SequenceToSequenceModelSpec
SequenceToSequenceModelSpecSequenceToSequenceModelSpec.__init__()SequenceToSequenceModelSpec.get_default_config()SequenceToSequenceModelSpec.get_source_vocabulary_size()SequenceToSequenceModelSpec.get_target_vocabulary_size()SequenceToSequenceModelSpec.optimize()SequenceToSequenceModelSpec.register_file()SequenceToSequenceModelSpec.register_source_vocabulary()SequenceToSequenceModelSpec.register_target_vocabulary()SequenceToSequenceModelSpec.register_vocabulary_mapping()SequenceToSequenceModelSpec.save()SequenceToSequenceModelSpec.validate()SequenceToSequenceModelSpec.variables()SequenceToSequenceModelSpec.configSequenceToSequenceModelSpec.nameSequenceToSequenceModelSpec.revision
- TransformerDecoderModelSpec
TransformerDecoderModelSpecTransformerDecoderModelSpec.__init__()TransformerDecoderModelSpec.from_config()TransformerDecoderModelSpec.get_default_config()TransformerDecoderModelSpec.get_vocabulary_size()TransformerDecoderModelSpec.optimize()TransformerDecoderModelSpec.register_file()TransformerDecoderModelSpec.register_vocabulary()TransformerDecoderModelSpec.save()TransformerDecoderModelSpec.validate()TransformerDecoderModelSpec.variables()TransformerDecoderModelSpec.configTransformerDecoderModelSpec.nameTransformerDecoderModelSpec.revision
- TransformerDecoderSpec
- TransformerEncoderModelSpec
TransformerEncoderModelSpecTransformerEncoderModelSpec.__init__()TransformerEncoderModelSpec.get_default_config()TransformerEncoderModelSpec.get_vocabulary_size()TransformerEncoderModelSpec.optimize()TransformerEncoderModelSpec.register_file()TransformerEncoderModelSpec.register_vocabulary()TransformerEncoderModelSpec.save()TransformerEncoderModelSpec.validate()TransformerEncoderModelSpec.variables()TransformerEncoderModelSpec.configTransformerEncoderModelSpec.nameTransformerEncoderModelSpec.revision
- TransformerEncoderSpec
- TransformerSpec
TransformerSpecTransformerSpec.__init__()TransformerSpec.from_config()TransformerSpec.get_default_config()TransformerSpec.get_source_vocabulary_size()TransformerSpec.get_target_vocabulary_size()TransformerSpec.optimize()TransformerSpec.register_file()TransformerSpec.register_source_vocabulary()TransformerSpec.register_target_vocabulary()TransformerSpec.register_vocabulary_mapping()TransformerSpec.save()TransformerSpec.validate()TransformerSpec.variables()TransformerSpec.configTransformerSpec.nameTransformerSpec.revision
- Wav2Vec2BertSpec
Wav2Vec2BertSpecWav2Vec2BertSpec.__init__()Wav2Vec2BertSpec.get_default_config()Wav2Vec2BertSpec.get_vocabulary_size()Wav2Vec2BertSpec.optimize()Wav2Vec2BertSpec.register_file()Wav2Vec2BertSpec.register_vocabulary()Wav2Vec2BertSpec.save()Wav2Vec2BertSpec.validate()Wav2Vec2BertSpec.variables()Wav2Vec2BertSpec.configWav2Vec2BertSpec.nameWav2Vec2BertSpec.revision
- Wav2Vec2Spec
Wav2Vec2SpecWav2Vec2Spec.__init__()Wav2Vec2Spec.get_default_config()Wav2Vec2Spec.get_vocabulary_size()Wav2Vec2Spec.optimize()Wav2Vec2Spec.register_file()Wav2Vec2Spec.register_vocabulary()Wav2Vec2Spec.save()Wav2Vec2Spec.validate()Wav2Vec2Spec.variables()Wav2Vec2Spec.configWav2Vec2Spec.nameWav2Vec2Spec.revision
- WhisperSpec