experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Remove unused sample rate param from API

Browse Source
This commit is contained in:
Reuben Morais 2019-10-09 16:34:38 +02:00
parent 42726b3612
commit 2f4116695f
3 changed files with 55 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
native_client/deepspeech.cc
View File

@ -318,7 +318,6 @@ DS_EnableDecoderWithLM(ModelState* aCtx,
int
DS_CreateStream(ModelState* aCtx,
unsigned int aSampleRate,
StreamingState** retval)
{
*retval = nullptr;
@ -383,11 +382,10 @@ DS_FinishStreamWithMetadata(StreamingState* aSctx)
StreamingState*
CreateStreamAndFeedAudioContent(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int aSampleRate)
unsigned int aBufferSize)
{
StreamingState* ctx;
int status = DS_CreateStream(aCtx, aSampleRate, &ctx);
int status = DS_CreateStream(aCtx, &ctx);
if (status != DS_ERR_OK) {
return nullptr;
}
@ -398,20 +396,18 @@ CreateStreamAndFeedAudioContent(ModelState* aCtx,
char*
DS_SpeechToText(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int aSampleRate)
unsigned int aBufferSize)
{
StreamingState* ctx = CreateStreamAndFeedAudioContent(aCtx, aBuffer, aBufferSize, aSampleRate);
StreamingState* ctx = CreateStreamAndFeedAudioContent(aCtx, aBuffer, aBufferSize);
return DS_FinishStream(ctx);
}
Metadata*
DS_SpeechToTextWithMetadata(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int aSampleRate)
unsigned int aBufferSize)
{
StreamingState* ctx = CreateStreamAndFeedAudioContent(aCtx, aBuffer, aBufferSize, aSampleRate);
StreamingState* ctx = CreateStreamAndFeedAudioContent(aCtx, aBuffer, aBufferSize);
return DS_FinishStreamWithMetadata(ctx);
}

16
native_client/deepspeech.h
View File

@ -124,9 +124,8 @@ int DS_EnableDecoderWithLM(ModelState* aCtx,
*
* @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate
* sample rate.
* sample rate (matching what the model was trained on).
* @param aBufferSize The number of samples in the audio signal.
* @param aSampleRate The sample-rate of the audio signal.
*
* @return The STT result. The user is responsible for freeing the string using
* {@link DS_FreeString()}. Returns NULL on error.
@ -134,8 +133,7 @@ int DS_EnableDecoderWithLM(ModelState* aCtx,
DEEPSPEECH_EXPORT
char* DS_SpeechToText(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int aSampleRate);
unsigned int aBufferSize);
/**
* @brief Use the DeepSpeech model to perform Speech-To-Text and output metadata
@ -143,9 +141,8 @@ char* DS_SpeechToText(ModelState* aCtx,
*
* @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate
* sample rate.
* sample rate (matching what the model was trained on).
* @param aBufferSize The number of samples in the audio signal.
* @param aSampleRate The sample-rate of the audio signal.
*
* @return Outputs a struct of individual letters along with their timing information.
* The user is responsible for freeing Metadata by calling {@link DS_FreeMetadata()}. Returns NULL on error.
@ -153,8 +150,7 @@ char* DS_SpeechToText(ModelState* aCtx,
DEEPSPEECH_EXPORT
Metadata* DS_SpeechToTextWithMetadata(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int aSampleRate);
unsigned int aBufferSize);
/**
* @brief Create a new streaming inference state. The streaming state returned
@ -162,7 +158,6 @@ Metadata* DS_SpeechToTextWithMetadata(ModelState* aCtx,
* and {@link DS_FinishStream()}.
*
* @param aCtx The ModelState pointer for the model to use.
* @param aSampleRate The sample-rate of the audio signal.
* @param[out] retval an opaque pointer that represents the streaming state. Can
* be NULL if an error occurs.
*
@ -170,7 +165,6 @@ Metadata* DS_SpeechToTextWithMetadata(ModelState* aCtx,
*/
DEEPSPEECH_EXPORT
int DS_CreateStream(ModelState* aCtx,
unsigned int aSampleRate,
StreamingState** retval);
/**
@ -178,7 +172,7 @@ int DS_CreateStream(ModelState* aCtx,
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
* @param aBuffer An array of 16-bit, mono raw audio samples at the
* appropriate sample rate.
* appropriate sample rate (matching what the model was trained on).
* @param aBufferSize The number of samples in @p aBuffer.
*/
DEEPSPEECH_EXPORT

47
native_client/deepspeech_compat.h
View File

@ -71,17 +71,17 @@ int DS_EnableDecoderWithLM(ModelState* aCtx,
* and {@link DS_FinishStream()}.
*
* @param aCtx The ModelState pointer for the model to use.
* @param aSampleRate The sample-rate of the audio signal.
* @param aSampleRate UNUSED, DEPRECATED.
* @param[out] retval an opaque pointer that represents the streaming state. Can
* be NULL if an error occurs.
*
* @return Zero for success, non-zero on failure.
*/
int DS_SetupStream(ModelState* aCtx,
unsigned int aSampleRate,
unsigned int /*aSampleRate*/,
StreamingState** retval)
{
return DS_CreateStream(aCtx, aSampleRate, retval);
return DS_CreateStream(aCtx, retval);
}
/**
@ -98,4 +98,45 @@ void DS_DiscardStream(StreamingState* aSctx)
return DS_FreeStream(aSctx);
}
/**
* @brief Use the DeepSpeech model to perform Speech-To-Text.
*
* @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate
* sample rate.
* @param aBufferSize The number of samples in the audio signal.
* @param aSampleRate UNUSED, DEPRECATED.
*
* @return The STT result. The user is responsible for freeing the string using
* {@link DS_FreeString()}. Returns NULL on error.
*/
char* DS_SpeechToText(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int /*aSampleRate*/)
{
return DS_SpeechToText(aCtx, aBuffer, aBufferSize);
}
/**
* @brief Use the DeepSpeech model to perform Speech-To-Text and output metadata
* about the results.
*
* @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate
* sample rate.
* @param aBufferSize The number of samples in the audio signal.
* @param aSampleRate UNUSED, DEPRECATED.
*
* @return Outputs a struct of individual letters along with their timing information.
* The user is responsible for freeing Metadata by calling {@link DS_FreeMetadata()}. Returns NULL on error.
*/
Metadata* DS_SpeechToTextWithMetadata(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int /*aSampleRate*/)
{
return DS_SpeechToTextWithMetadata(aCtx, aBuffer, aBufferSize);
}
#endif /* DEEPSPEECH_COMPAT_H */