Comments (4)
Forgot to say thanks for the helpers!! I will highly appreciate it!
from deepspeech-examples.
from deepspeech-examples.
from deepspeech-examples.
In case this would help,
I recorded myself twice using the microphone quality setting set to 44100hz, I recorded one at 44.1khz and the other on 16khz since I recently found other speech services to work better when I do that, here are the recordings:
(Searched google for upload files forever and uploaded it as 7z since I had trouble putting it here): https://usaupload.com/5Kvd/test-voices.7z
I recorded my voice using the following script I had:
import pyaudio, wave, time, sys, os
from datetime import datetime
CHUNK = 8192
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
RECORD_SECONDS = 4
#current_time = str(datetime.now()) #"Date/Time for File Name"
#current_time = "_".join(current_time.split()).replace(":","-")
#current_time = current_time[:-7]
#file_name = 'Audio_'+current_time+'.wav'
WAVE_OUTPUT_FILENAME = 'test.wav'
try:
os.remove(WAVE_OUTPUT_FILENAME)
except:
print("Nothing to clean")
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, channels = CHANNELS, rate = RATE, input = True, input_device_index = 0, frames_per_buffer = CHUNK)
print("* recording")
frames = []
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
print(i)
data = stream.read(CHUNK)
frames.append(data)
print("* done recording")
stream.stop_stream()
stream.close()
p.terminate()
wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()
record.cmd:
@echo off
call C:\Users\%username%\anaconda3\Scripts\activate.bat "C:\Users\%username%\anaconda3" & python record.py
pause
simply swapped RATE to 16000 and recorded again since these recordings always worked better than 44100 so I tested both just to be sure..
would be worth mentioning that I never actually tested any .wav files against DeepSpeech, just my microphone, which works as demonstrated above, what I meant is that I tested those wav files against "competitors" and it worked there, also my microphone worked there, just for reference.
from deepspeech-examples.
Related Issues (20)
- Error while running HOT 1
- Corrupt SRT output
- Run mic_vad_streaming.py got error HOT 1
- Cannot find DOWNSAMPLING_WORKER for Web Microphone Websocket streaming HOT 1
- pyaudio setup error HOT 2
- [Android] Could not find org.mozilla.deepspeech:libdeepspeech:0.9.3. HOT 1
- cannot find node_modules/deepspeech/lib/binding/v0.9.3/linux-x64/node-v93/deepspeech.node HOT 7
- Deepspeech C# crashes
- pause ASR when speaker is outputting
- not starting
- Cannot connect to server socket err = No such file or directory Cannot connect to server request channel
- .Net Framework example missing DeepSpeechClient solution? HOT 1
- tc-tests-utils.sh not found HOT 1
- Non authorized instruction
- Cannot find the model file: deepspeech-0.9.3-models.pbmm HOT 2
- Error: Could not locate the bindings file. Tried:
- Accuracy is too low in 0.9.3 model HOT 1
- Failed to execute startup script HOT 1
- Not getting stt with nodejs
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepspeech-examples.