aws-transcribe

问题 This is a follow-on question to AWS Transcribe S3 .wav file to text. I use a stream to read and send a .wav file contents to AWS. Instead of getting back the correct transcript, I get nonsense like a bunch of "Yeah." statements. It looks like AWS isn't able to interpret the byte stream correctly, but I'm not sure what's wrong. I'm wondering if the file needs to be encoded somehow, ie, I can't send the raw .wav bytes straight from the file? Or perhaps I need to tell the service that this is

问题 I am trying to use aws Transcribe to convert a wav file to text. I have uploaded a wav file to S3, which is located here and it has public read/write permissions: https://s3.us-east-1.amazonaws.com/csld8xmsdksdf8s9sk3mmdjsdifkjksdijsldk/Transcribe2.wav. The wav file is valid. I can download it in my browser and replay it (and it sounds like the origin recording), so I think we can rule out an invalid input file, file permissions, etc. I am using java version: 1.8.0_275 for mac. I expect my

问题 I am working on a whatsapp chatbot where I receive audio file(ogg format) file url from Whatsapp and I get buffer and upload that file on S3(sample.ogg) Now what is want to use AWS Transcribe Streaming so I am creating readStream of file and sending to AWS transcribe I am using websocket but I am receiving Empty response of Sometimes when I Mhm mm mm response. Please can anyone tell what wrong I am doing in my code const express = require('express') const app = express() const fs = require(

问题 How to feed the audio stream output of the AWS Kinesis video stream (KVS) to AWS Transcribe service and get realtime audio to text conversion? I ingested audio via amazon connect to KVS(Kinesis video stream), My concern is, which format kinesis video stream (KVS) deliver (I hope its Payload format) and will Transcribe service able to support it or any way I can convert to Transcribe service understandable. 回答1: For me, I tinkered with the AWS CLI, two stage process although the output from

问题 Hi My requirement is I have live audio stream as input, say a call between 2 people, now to convert that audio to text on live and pick certain keywords from that extracted text and insert in Database. As per architecture in https://github.com/aws-samples/amazon-connect-realtime-transcription Both AWS Kinesis Video Streams service and AWS Transcribe used for live streaming but as per link : https://aws.amazon.com/blogs/machine-learning/amazon-transcribe-now-supports-real-time-transcriptions/

问题 I'm working with the Amazon Transcribe service and trying to get CloudWatch Events to fire a Lambda function that executes a POST request to my API. Here's the Lambda function var querystring = require('querystring'); var http = require('http'); exports.handler = function(event, context) { var post_data = querystring.stringify( event ); // An object of options to indicate where to post to var post_options = { host: '193e561e.ngrok.io', port: '80', path: '/api/lambda', method: 'POST', headers:

问题 I am trying to use Amazon's new streaming transcribe API from Go 1.11. Currently Amazon provides Java SDK only so I am trying the low-level way. The only relevant piece of documentation is here but it does not show the endpoint. I have found it in a Java example that it is https://transcribestreaming.<region>.amazonaws.com and I am trying the Ireland region i.e. https://transcribestreaming.eu-west-1.amazonaws.com . Here is my code to open an HTTP/2 bi-directional stream: import ( "crypto/tls"