# Copyright 2019 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # NOTE: This file is auto generated by the elixir code generator program. # Do not edit this file manually. defmodule GoogleApi.Speech.V1.Model.RecognitionConfig do @moduledoc """ Provides information to the recognizer that specifies how to process the request. ## Attributes * `audioChannelCount` (*type:* `integer()`, *default:* `nil`) - *Optional* The number of channels in the input audio data. ONLY set this for MULTI-CHANNEL recognition. Valid values for LINEAR16 and FLAC are `1`-`8`. Valid values for OGG_OPUS are '1'-'254'. Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`. If `0` or omitted, defaults to one channel (mono). Note: We only recognize the first channel by default. To perform independent recognition on each channel set `enable_separate_recognition_per_channel` to 'true'. * `enableAutomaticPunctuation` (*type:* `boolean()`, *default:* `nil`) - *Optional* If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. Note: This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature. * `enableSeparateRecognitionPerChannel` (*type:* `boolean()`, *default:* `nil`) - This needs to be set to `true` explicitly and `audio_channel_count` > 1 to get each channel recognized separately. The recognition result will contain a `channel_tag` field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized: `audio_channel_count` multiplied by the length of the audio. * `enableWordTimeOffsets` (*type:* `boolean()`, *default:* `nil`) - *Optional* If `true`, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If `false`, no word-level time offset information is returned. The default is `false`. * `encoding` (*type:* `String.t`, *default:* `nil`) - Encoding of audio data sent in all `RecognitionAudio` messages. This field is optional for `FLAC` and `WAV` audio files and required for all other audio formats. For details, see AudioEncoding. * `languageCode` (*type:* `String.t`, *default:* `nil`) - *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: "en-US". See [Language Support](https://cloud.google.com/speech-to-text/docs/languages) for a list of the currently supported language codes. * `maxAlternatives` (*type:* `integer()`, *default:* `nil`) - *Optional* Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechRecognitionResult`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one. * `metadata` (*type:* `GoogleApi.Speech.V1.Model.RecognitionMetadata.t`, *default:* `nil`) - *Optional* Metadata regarding this request. * `model` (*type:* `String.t`, *default:* `nil`) - *Optional* Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig.
Model Description
command_and_search Best for short queries such as voice commands or voice search.
phone_call Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate).
video Best for audio that originated from from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate.
default Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate.
* `profanityFilter` (*type:* `boolean()`, *default:* `nil`) - *Optional* If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. "f***". If set to `false` or omitted, profanities won't be filtered out. * `sampleRateHertz` (*type:* `integer()`, *default:* `nil`) - Sample rate in Hertz of the audio data sent in all `RecognitionAudio` messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding. * `speechContexts` (*type:* `list(GoogleApi.Speech.V1.Model.SpeechContext.t)`, *default:* `nil`) - *Optional* array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see [speech adaptation](https://cloud.google.com/speech-to-text/docs/context-strength). * `useEnhanced` (*type:* `boolean()`, *default:* `nil`) - *Optional* Set to true to use an enhanced model for speech recognition. If `use_enhanced` is set to true and the `model` field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio. If `use_enhanced` is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model. """ use GoogleApi.Gax.ModelBase @type t :: %__MODULE__{ :audioChannelCount => integer(), :enableAutomaticPunctuation => boolean(), :enableSeparateRecognitionPerChannel => boolean(), :enableWordTimeOffsets => boolean(), :encoding => String.t(), :languageCode => String.t(), :maxAlternatives => integer(), :metadata => GoogleApi.Speech.V1.Model.RecognitionMetadata.t(), :model => String.t(), :profanityFilter => boolean(), :sampleRateHertz => integer(), :speechContexts => list(GoogleApi.Speech.V1.Model.SpeechContext.t()), :useEnhanced => boolean() } field(:audioChannelCount) field(:enableAutomaticPunctuation) field(:enableSeparateRecognitionPerChannel) field(:enableWordTimeOffsets) field(:encoding) field(:languageCode) field(:maxAlternatives) field(:metadata, as: GoogleApi.Speech.V1.Model.RecognitionMetadata) field(:model) field(:profanityFilter) field(:sampleRateHertz) field(:speechContexts, as: GoogleApi.Speech.V1.Model.SpeechContext, type: :list) field(:useEnhanced) end defimpl Poison.Decoder, for: GoogleApi.Speech.V1.Model.RecognitionConfig do def decode(value, options) do GoogleApi.Speech.V1.Model.RecognitionConfig.decode(value, options) end end defimpl Poison.Encoder, for: GoogleApi.Speech.V1.Model.RecognitionConfig do def encode(value, options) do GoogleApi.Gax.ModelBase.encode(value, options) end end