Watson Speech to Text

El servicio Speech to Text convierte la voz humana en palabras escritas. Se puede utilizar en cualquier lugar donde se necesite llenar el hueco entre la palabra hablada y la forma escrita, incluido el control de voz de los sistemas incorporados, la transcripción de reuniones y teleconferencias y el dictado de correo electrónico y notas.

El modelo de idioma español Colombia es: model=es-CO_BroadbandModel

Qué bonito es cuando sí funciona jaja
![](

la verdad no me funciono coomo esperaba, envie dos audios.

1. hola soy julian orozco y soy de “ciudad”
   “confidence”: 0.36,
   “transcript”: "when I started my number is called auto school showed up there you go "
2. estados unidos de norte america
   "confidence": 0.5,
   “transcript”: "espousal near the North America "
   nos se si hay que configurar el idioma de entrada o que paso aca.

Un pequeño comentario, se pone la url justo antes de v1, pues por ejemplo a mi no me aparece “api” al final de mi url:

curl -X POST -u "apikey:SPkIfPpktELAu5mS0fR2D6eQz5fvGFUUdbxGzzmWz2wz" \
 --header "Content-Type: audio/flac" --data-binary @audio-file2.flac \
  "https://api.us-south.speech-to-text.watson.cloud.ibm.com/instances/219b75ae-b66c-4993-b2d6-06025c1813a4/v1/recognize?model=es-MX_BroadbandModel&keywords=%22isaac%22&keywords_threshold=0.5"

¿Las malas palabras estan incluidas en Watson Speech to Text? no lo encontre en el docs https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-gettingStarted

Con los audios de la clase funciona bien pero al grabar un audio con el celular y enviarlo ya no funciona, dice error 400, en el reproductor que uso (VCL) se reproduce bien, la solucion fue tomar el archivo original y pasarlo por un conversor a flac y en este caso si funciono

Me funciono igual.
“transcript”: "cuéllar isaac gracias por tomar este curso sígueme mi redes en instagram estoy como el buen isi y en lo demás como isaac carranza "

Excelente clase

¿Alguien me podría ayudar? me sale lo siguiente:
“keywords” no se reconoce como un comando interno o externo,
programa o archivo por lotes ejecutable.
“keywords_threshold” no se reconoce como un comando interno o externo,
programa o archivo por lotes ejecutable.

Solo recibe audios .flac? Como se configura que idioma es el que debe transcribir?

Muy poderosa la herramienta de Speech to text.

Instagram @elbuenizzy

Hola, alguien me podría ayudar no me sale he hecho de todo. Me sale un mensaje muy largo solo colocaré una parte:
-F, --form <name=content> Specify HTTP multipart POST data
–form-string <name=string> Specify HTTP multipart POST data
–ftp-account <data> Account data string
–ftp-alternative-to-user <command> String to replace USER [name]
–ftp-create-dirs Create the remote dirs if not present
–ftp-method <method> Control CWD usage
–ftp-pasv Use PASV/EPSV instead of PORT
-P, --ftp-port <address> Use PORT instead of PASV
–ftp-pret Send PRET before PASV
–ftp-skip-pasv-ip Skip the IP address for PASV
–ftp-ssl-ccc Send CCC after authenticating
–ftp-ssl-ccc-mode <active/passive> Set CCC mode
–ftp-ssl-control Require SSL/TLS for FTP login, clear for transfer
-G, --get Put the post data in the URL and use GET
-g, --globoff Disable URL sequences and ranges using {} and []
-I, --head Show document info only
-H, --header header/@file Pass custom header(s) to server
-h, --help This help text
–hostpubmd5 <md5> Acceptable MD5 hash of the host public key
-0, --http1.0 Use HTTP 1.0
–http1.1 Use HTTP 1.1
–http2 Use HTTP 2
–http2-prior-knowledge Use HTTP 2 without HTTP/1.1 Upgrade
–ignore-content-length Ignore the size of the remote resource
-i, --include Include protocol response headers in the output
-k, --insecure Allow insecure server connections when using SSL
–interface <name> Use network INTERFACE (or address)
-4, --ipv4 Resolve names to IPv4 addresses
-6, --ipv6 Resolve names to IPv6 addresses
-j, --junk-session-cookies Ignore session cookies read from file
–keepalive-time <seconds> Interval time for keepalive probes
–key <key> Private key file name
–key-type <type> Private key file type (DER/PEM/ENG)
–krb <level> Enable Kerberos with security <level>
–libcurl <file> Dump libcurl equivalent code of this command line
–limit-rate <speed> Limit transfer speed to RATE
-l, --list-only List only mode
–local-port <num/range> Force use of RANGE for local port numbers
-L, --location Follow redirects
–location-trusted Like --location, and send auth to other hosts
–login-options <options> Server login options
–mail-auth <address> Originator address of the original email
–mail-from <address> Mail from this address
–mail-rcpt <address> Mail from this address
-M, --manual Display the full manual
–max-filesize <bytes> Maximum file size to download
–max-redirs <num> Maximum number of redirects allowed
-m, --max-time <time> Maximum time allowed for the transfer
–metalink Process given URLs as metalink XML file
–negotiate Use HTTP Negotiate (SPNEGO) authentication
-n, --netrc Must read .netrc for user name and password
–netrc-file <filename> Specify FILE for netrc
–netrc-optional Use either .netrc or URL
-:, --next Make next URL use its separate set of options
–no-alpn Disable the ALPN TLS extension
-N, --no-buffer Disable buffering of the output stream
–no-keepalive Disable TCP keepalive on the connection
–no-npn Disable the NPN TLS extension
–no-sessionid Disable SSL session-ID reusing
–noproxy <no-proxy-list> List of hosts which do not use proxy
–ntlm Use HTTP NTLM authentication
–ntlm-wb Use HTTP NTLM authentication with winbind
–oauth2-bearer <token> OAuth 2 Bearer Token
-o, --output <file> Write to file instead of stdout
–pass <phrase> Pass phrase for the private key
–path-as-is Do not squash … sequences in URL path
–pinnedpubkey <hashes> FILE/HASHES Public key to verify peer against
–post301 Do not switch to GET after following a 301
–post302 Do not switch to GET after following a 302
–post303 Do not switch to GET after following a 303
–preproxy [protocol://]host[:port] Use this proxy first
-#, --progress-bar Display transfer progress as a bar
–proto <protocols> Enable/disable PROTOCOLS
–proto-default <protocol> Use PROTOCOL for any URL missing a scheme
–proto-redir <protocols> Enable/disable PROTOCOLS on redirect
-x, --proxy [protocol://]host[:port] Use this proxy
–proxy-anyauth Pick any proxy authentication method
–proxy-basic Use Basic authentication on the proxy
–proxy-cacert <file> CA certificate to verify peer against for proxy
–proxy-capath <dir> CA directory to verify peer against for proxy
–proxy-cert <cert[:passwd]> Set client certificate for proxy
–proxy-cert-type <type> Client certificate type for HTTS proxy
–proxy-ciphers <list> SSL ciphers to use for proxy
–proxy-crlfile <file> Set a CRL list for proxy
–proxy-digest Use Digest authentication on the proxy
–proxy-header header/@file Pass custom header(s) to proxy
–proxy-insecure Do HTTPS proxy connections without verifying the proxy
–proxy-key <key> Private key for HTTPS proxy
–proxy-key-type <type> Private key file type for proxy
–proxy-negotiate Use HTTP Negotiate (SPNEGO) authentication on the proxy
–proxy-ntlm Use NTLM authentication on the proxy
–proxy-pass <phrase> Pass phrase for the private key for HTTPS proxy
–proxy-service-name <name> SPNEGO proxy service name
–proxy-ssl-allow-beast Allow security flaw for interop for HTTPS proxy
–proxy-tlsauthtype <type> TLS authentication type for HTTPS proxy
–proxy-tlspassword <string> TLS password for HTTPS proxy
–proxy-tlsuser <name> TLS username for HTTPS proxy
–proxy-tlsv1 Use TLSv1 for HTTPS proxy
-U, --proxy-user user:password Proxy user and password
–proxy1.0 <host[:port]> Use HTTP/1.0 proxy on given port
-p, --proxytunnel Operate through a HTTP proxy tunnel (using CONNECT)
–pubkey <key> SSH Public key file name
-Q, --quote Send command(s) to server before transfer
–random-file <file> File for reading random data from
-r, --range <range> Retrieve only the bytes within RANGE
–raw Do HTTP “raw”; no transfer decoding
-e, --referer <URL> Referrer URL
-J, --remote-header-name Use the header-provided filename
-O, --remote-name Write output to a file named as the remote file
–remote-name-all Use the remote file name for all URLs
-R, --remote-time Set the remote file’s time on the local output
-X, --request <command> Specify request command to use
–request-target Specify the target for this request
–resolve host:port:address Resolve the host+port to this address
–retry <num> Retry request if transient problems occur
–retry-connrefused Retry on connection refused (use with --retry)
–retry-delay <seconds> Wait time between retries
–retry-max-time <seconds> Retry only within this period
–sasl-ir Enable initial response in SASL authentication
–service-name <name> SPNEGO service name
-S, --show-error Show error even when -s is used
-s, --silent Silent mode
–socks4 <host[:port]> SOCKS4 proxy on given host + port
–socks4a <host[:port]> SOCKS4a proxy on given host + port
–socks5 <host[:port]> SOCKS5 proxy on given host + port
–socks5-basic Enable username/password auth for SOCKS5 proxies
–socks5-gssapi Enable GSS-API auth for SOCKS5 proxies
–socks5-gssapi-nec Compatibility with NEC SOCKS5 server
–socks5-gssapi-service <name> SOCKS5 proxy service name for GSS-API
–socks5-hostname <host[:port]> SOCKS5 proxy, pass host name to proxy
-Y, --speed-limit <speed> Stop transfers slower than this
-y, --speed-time <seconds> Trigger ‘speed-limit’ abort after this time
–ssl Try SSL/TLS
–ssl-allow-beast Allow security flaw to improve interop
–ssl-no-revoke Disable cert revocation checks (WinSSL)
–ssl-reqd Require SSL/TLS
-2, --sslv2 Use SSLv2
-3, --sslv3 Use SSLv3
–stderr Where to redirect stderr
–suppress-connect-headers Suppress proxy CONNECT response headers
–tcp-fastopen Use TCP Fast Open
–tcp-nodelay Use the TCP_NODELAY option
-t, --telnet-option <opt=val> Set telnet option
–tftp-blksize <value> Set TFTP BLKSIZE option
–tftp-no-options Do not send any TFTP options
-z, --time-cond <time> Transfer based on a time condition
–tls-max <VERSION> Use TLSv1.0 or greater
–tlsauthtype <type> TLS authentication type
–tlspassword TLS password
–tlsuser <name> TLS user name
-1, --tlsv1 Use TLSv1.0 or greater
–tlsv1.0 Use TLSv1.0
–tlsv1.1 Use TLSv1.1
–tlsv1.2 Use TLSv1.2
–tlsv1.3 Use TLSv1.3
–tr-encoding Request compressed transfer encoding
–trace <file> Write a debug trace to FILE
–trace-ascii <file> Like --trace, but without hex output
–trace-time Add time stamps to trace/verbose output
–unix-socket <path> Connect through this Unix domain socket
-T, --upload-file <file> Transfer local FILE to destination
–url <url> URL to work with
-B, --use-ascii Use ASCII/text transfer
-u, --user user:password Server user and password
-A, --user-agent <name> Send User-Agent <name> to server
-v, --verbose Make the operation more talkative
-V, --version Show version number and quit
-w, --write-out <format> Use output FORMAT after completion
–xattr Store metadata in extended file attributes

Super interesante 😃

Seria interesante ver cómo agregar la inteligencia a los textos, por ejemplo poner el keyword nombre y que el me devuelva el nombre. Asi como en el ML UNL

para lo que utilizan windows (como yo):

curl -X POST -u "apikey:{apikey}" --header "Content-Type: audio/flac" --data-binary @audio-file2.flac "{url}/v1/recognize?model=es-MX_BroadbandModel&keywords=%22isaac%22&keywords_threshold=0.5"

Aporte. Lo probé con formato .ogg y funciona muy bien.

Saludos!

Buen servicio!

Que bueno cuando todo te funciona.

Funcionó perfecto en los dos casos de ejemplo, realizados por el profesor. Al parecer el servicio funciona con archivos de audio guardados con la extensión .flac.

Lo probé con un archivo .wav y funcionó perfecto!