[−][src]Crate deepspeech_sys
Structs
Metadata | @brief Stores the entire CTC output as an array of character metadata objects |
MetadataItem | @brief Stores each individual character, along with its timing information |
ModelState | |
StreamingState | |
max_align_t |
Constants
Functions
DS_CreateModel⚠ | @brief An object providing an interface to a trained DeepSpeech model. |
DS_CreateStream⚠ | @brief Create a new streaming inference state. The streaming state returned by this function can then be passed to {@link DS_FeedAudioContent()} and {@link DS_FinishStream()}. |
DS_EnableDecoderWithLM⚠ | @brief Enable decoding using beam scoring with a KenLM language model. |
DS_FeedAudioContent⚠ | @brief Feed audio samples to an ongoing streaming inference. |
DS_FinishStream⚠ | @brief Signal the end of an audio signal to an ongoing streaming inference, returns the STT result over the whole audio signal. |
DS_FinishStreamWithMetadata⚠ | @brief Signal the end of an audio signal to an ongoing streaming inference, returns per-letter metadata. |
DS_FreeMetadata⚠ | @brief Free memory allocated for metadata information. |
DS_FreeModel⚠ | @brief Frees associated resources and destroys model object. |
DS_FreeStream⚠ | @brief Destroy a streaming state without decoding the computed logits. This can be used if you no longer need the result of an ongoing streaming inference and don't want to perform a costly decode operation. |
DS_FreeString⚠ | @brief Free a char* string returned by the DeepSpeech API. |
DS_GetModelSampleRate⚠ | @brief Return the sample rate expected by a model. |
DS_IntermediateDecode⚠ | @brief Compute the intermediate decoding of an ongoing streaming inference. |
DS_PrintVersions⚠ | @brief Print version of this library and of the linked TensorFlow library. |
DS_SpeechToText⚠ | @brief Use the DeepSpeech model to perform Speech-To-Text. |
DS_SpeechToTextWithMetadata⚠ | @brief Use the DeepSpeech model to perform Speech-To-Text and output metadata about the results. |
Type Definitions
DeepSpeech_Error_Codes |