mirrors/DeepSpeech
2
0
Fork 0
mirror of https://github.com/mozilla/DeepSpeech.git synced 2025-10-26 11:19:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1088 from wgent/patch-1

Browse Source 
[Docs] Renames output_model.pb to output_graph.pb in README

X-DeepSpeech: NOBUILD
This commit is contained in:
lissyx 2017-12-13 19:37:02 +01:00 committed by GitHub
commit 7735ac7c24
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -15,14 +15,14 @@ Once everything is installed you can then use the `deepspeech` binary to do spee
```bash
pip install deepspeech
deepspeech models/output_model.pb my_audio_file.wav models/alphabet.txt
deepspeech models/output_graph.pb my_audio_file.wav models/alphabet.txt
```
Alternatively, quicker inference (The realtime factor on a GeForce GTX 1070 is about 0.44.) can be performed using a supported NVIDIA GPU on Linux. (See the release notes to find which GPU's are supported.) This is done by instead installing the GPU specific package:
```bash
pip install deepspeech-gpu
deepspeech models/output_model.pb my_audio_file.wav models/alphabet.txt
deepspeech models/output_graph.pb my_audio_file.wav models/alphabet.txt
```
See the output of `deepspeech -h` for more information on the use of `deepspeech`. (If you experience problems running `deepspeech`, please check [required runtime dependencies](native_client/README.md#required-dependencies)).
@ -133,7 +133,7 @@ In both cases, it should take care of installing all the required dependencies.
Note: the following command assumes you [downloaded the pre-trained model](#getting-the-pre-trained-model).
```bash
deepspeech models/output_model.pb my_audio_file.wav models/alphabet.txt models/lm.binary models/trie
deepspeech models/output_graph.pb my_audio_file.wav models/alphabet.txt models/lm.binary models/trie
```
The last two arguments are optional, and represent a language model.
@ -159,7 +159,7 @@ This will download `native_client.tar.xz` which includes the deepspeech binary a
Note: the following command assumes you [downloaded the pre-trained model](#getting-the-pre-trained-model).
```bash
./deepspeech models/output_model.pb audio_input.wav models/alphabet.txt models/lm.binary models/trie
./deepspeech models/output_graph.pb audio_input.wav models/alphabet.txt models/lm.binary models/trie
```