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

Sync all the docs with sample rate changes 

X-DeepSpeech: NOBUILD
This commit is contained in:
Reuben Morais 2019-10-10 17:15:58 +02:00
parent 9200b720c3
commit 2b68c56025
6 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
native_client/deepspeech_compat.h
View File

@ -103,7 +103,7 @@ void DS_DiscardStream(StreamingState* aSctx)
* *
* @param aCtx The ModelState pointer for the model to use. * @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate * @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 aBufferSize The number of samples in the audio signal.
* @param aSampleRate UNUSED, DEPRECATED. * @param aSampleRate UNUSED, DEPRECATED.
* *
@ -124,7 +124,7 @@ char* DS_SpeechToText(ModelState* aCtx,
* *
* @param aCtx The ModelState pointer for the model to use. * @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate * @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 aBufferSize The number of samples in the audio signal.
* @param aSampleRate UNUSED, DEPRECATED. * @param aSampleRate UNUSED, DEPRECATED.
* *

6
native_client/dotnet/DeepSpeechClient/DeepSpeech.cs
View File

@ -148,7 +148,7 @@ namespace DeepSpeechClient
/// <summary> /// <summary>
/// Feeds audio samples to an ongoing streaming inference. /// Feeds audio samples to an ongoing streaming inference.
/// </summary> /// </summary>
/// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate.</param> /// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).</param>
public unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize) public unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize)
{ {
NativeImp.DS_FeedAudioContent(_streamingStatePP, aBuffer, aBufferSize); NativeImp.DS_FeedAudioContent(_streamingStatePP, aBuffer, aBufferSize);
@ -229,7 +229,7 @@ namespace DeepSpeechClient
/// <summary> /// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text. /// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary> /// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param> /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param> /// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <returns>The STT result. The user is responsible for freeing the string. Returns NULL on error.</returns> /// <returns>The STT result. The user is responsible for freeing the string. Returns NULL on error.</returns>
public unsafe string SpeechToText(short[] aBuffer, uint aBufferSize) public unsafe string SpeechToText(short[] aBuffer, uint aBufferSize)
@ -240,7 +240,7 @@ namespace DeepSpeechClient
/// <summary> /// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text. /// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary> /// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param> /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param> /// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <returns>The extended metadata. The user is responsible for freeing the struct. Returns NULL on error.</returns> /// <returns>The extended metadata. The user is responsible for freeing the struct. Returns NULL on error.</returns>
public unsafe Models.Metadata SpeechToTextWithMetadata(short[] aBuffer, uint aBufferSize) public unsafe Models.Metadata SpeechToTextWithMetadata(short[] aBuffer, uint aBufferSize)

6
native_client/dotnet/DeepSpeechClient/Interfaces/IDeepSpeech.cs
View File

@ -40,7 +40,7 @@ namespace DeepSpeechClient.Interfaces
/// <summary> /// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text. /// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary> /// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param> /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param> /// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <returns>The STT result. The user is responsible for freeing the string. Returns NULL on error.</returns> /// <returns>The STT result. The user is responsible for freeing the string. Returns NULL on error.</returns>
unsafe string SpeechToText(short[] aBuffer, unsafe string SpeechToText(short[] aBuffer,
@ -49,7 +49,7 @@ namespace DeepSpeechClient.Interfaces
/// <summary> /// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text. /// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary> /// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param> /// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param> /// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <returns>The extended metadata result. The user is responsible for freeing the struct. Returns NULL on error.</returns> /// <returns>The extended metadata result. The user is responsible for freeing the struct. Returns NULL on error.</returns>
unsafe Metadata SpeechToTextWithMetadata(short[] aBuffer, unsafe Metadata SpeechToTextWithMetadata(short[] aBuffer,
@ -81,7 +81,7 @@ namespace DeepSpeechClient.Interfaces
/// <summary> /// <summary>
/// Feeds audio samples to an ongoing streaming inference. /// Feeds audio samples to an ongoing streaming inference.
/// </summary> /// </summary>
/// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate.</param> /// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).</param>
unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize); unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize);
/// <summary> /// <summary>

6
native_client/java/libdeepspeech/src/main/java/org/mozilla/deepspeech/libdeepspeech/DeepSpeechModel.java
View File

@ -57,7 +57,7 @@ public class DeepSpeechModel {
* @brief Use the DeepSpeech model to perform Speech-To-Text. * @brief Use the DeepSpeech model to perform Speech-To-Text.
* *
* @param buffer A 16-bit, mono raw audio signal at the appropriate * @param buffer A 16-bit, mono raw audio signal at the appropriate
* sample rate. * sample rate (matching what the model was trained on).
* @param buffer_size The number of samples in the audio signal. * @param buffer_size The number of samples in the audio signal.
* *
* @return The STT result. * @return The STT result.
@ -71,7 +71,7 @@ public class DeepSpeechModel {
* about the results. * about the results.
* *
* @param buffer A 16-bit, mono raw audio signal at the appropriate * @param buffer A 16-bit, mono raw audio signal at the appropriate
* sample rate. * sample rate (matching what the model was trained on).
* @param buffer_size The number of samples in the audio signal. * @param buffer_size The number of samples in the audio signal.
* *
* @return Outputs a Metadata object of individual letters along with their timing information. * @return Outputs a Metadata object of individual letters along with their timing information.
@ -98,7 +98,7 @@ public class DeepSpeechModel {
* *
* @param cctx A streaming state pointer returned by createStream(). * @param cctx A streaming state pointer returned by createStream().
* @param buffer An array of 16-bit, mono raw audio samples at the * @param buffer 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 buffer_size The number of samples in @p buffer. * @param buffer_size The number of samples in @p buffer.
*/ */
public void feedAudioContent(DeepSpeechStreamingState ctx, short[] buffer, int buffer_size) { public void feedAudioContent(DeepSpeechStreamingState ctx, short[] buffer, int buffer_size) {

6
native_client/javascript/index.js
View File

@ -64,7 +64,7 @@ Model.prototype.enableDecoderWithLM = function() {
/** /**
* Use the DeepSpeech model to perform Speech-To-Text. * Use the DeepSpeech model to perform Speech-To-Text.
* *
* @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate. * @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
* @param {number} aBufferSize The number of samples in the audio signal. * @param {number} aBufferSize The number of samples in the audio signal.
* *
* @return {string} The STT result. Returns undefined on error. * @return {string} The STT result. Returns undefined on error.
@ -78,7 +78,7 @@ Model.prototype.stt = function() {
* Use the DeepSpeech model to perform Speech-To-Text and output metadata * Use the DeepSpeech model to perform Speech-To-Text and output metadata
* about the results. * about the results.
* *
* @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate. * @param {object} aBuffer A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
* @param {number} aBufferSize The number of samples in the audio signal. * @param {number} aBufferSize The number of samples in the audio signal.
* *
* @return {object} Outputs a :js:func:`Metadata` struct of individual letters along with their timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error. * @return {object} Outputs a :js:func:`Metadata` struct of individual letters along with their timing information. The user is responsible for freeing Metadata by calling :js:func:`FreeMetadata`. Returns undefined on error.
@ -111,7 +111,7 @@ Model.prototype.createStream = function() {
* *
* @param {object} aSctx A streaming state returned by :js:func:`Model.setupStream`. * @param {object} aSctx A streaming state returned by :js:func:`Model.setupStream`.
* @param {buffer} aBuffer An array of 16-bit, mono raw audio samples at the * @param {buffer} 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 {number} aBufferSize The number of samples in @param aBuffer. * @param {number} aBufferSize The number of samples in @param aBuffer.
*/ */
Model.prototype.feedAudioContent = function() { Model.prototype.feedAudioContent = function() {

6
native_client/python/__init__.py
View File

@ -69,7 +69,7 @@ class Model(object):
""" """
Use the DeepSpeech model to perform Speech-To-Text. Use the DeepSpeech model to perform Speech-To-Text.
:param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate. :param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
:type aBuffer: int array :type aBuffer: int array
:param aBufferSize: The number of samples in the audio signal. :param aBufferSize: The number of samples in the audio signal.
@ -84,7 +84,7 @@ class Model(object):
""" """
Use the DeepSpeech model to perform Speech-To-Text and output metadata about the results. Use the DeepSpeech model to perform Speech-To-Text and output metadata about the results.
:param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate. :param aBuffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
:type aBuffer: int array :type aBuffer: int array
:param aBufferSize: The number of samples in the audio signal. :param aBufferSize: The number of samples in the audio signal.
@ -117,7 +117,7 @@ class Model(object):
:param aSctx: A streaming state pointer returned by :func:`createStream()`. :param aSctx: A streaming state pointer returned by :func:`createStream()`.
:type aSctx: object :type aSctx: object
:param aBuffer: An array of 16-bit, mono raw audio samples at the appropriate sample rate. :param aBuffer: An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).
:type aBuffer: int array :type aBuffer: int array
:param aBufferSize: The number of samples in @p aBuffer. :param aBufferSize: The number of samples in @p aBuffer.